Merge pull request 'chore: release v4.0.0' (#151) from chore/release-v4.0.0 into development

Reviewed-on: #151

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Project management plugins with Gitea and NetBox integrations",
-    "version": "3.1.0"
+    "version": "4.0.0"
   },
   "plugins": [
     {
@@ -149,6 +149,22 @@
       "category": "development",
       "tags": ["code-review", "pull-requests", "security", "quality"],
       "license": "MIT"
+    },
+    {
+      "name": "data-platform",
+      "version": "1.0.0",
+      "description": "Data engineering tools with pandas, PostgreSQL/PostGIS, and dbt integration",
+      "source": "./plugins/data-platform",
+      "author": {
+        "name": "Leo Miranda",
+        "email": "leobmiranda@gmail.com"
+      },
+      "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/data-platform/README.md",
+      "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+      "mcpServers": ["./.mcp.json"],
+      "category": "data",
+      "tags": ["pandas", "postgresql", "postgis", "dbt", "data-engineering", "etl"],
+      "license": "MIT"
     }
   ]
 }

CHANGELOG.md

@@ -4,6 +4,80 @@ All notable changes to the Leo Claude Marketplace will be documented in this fil
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [4.0.0] - 2026-01-25
+
+### Added
+
+#### New Plugin: data-platform v1.0.0
+- **pandas MCP Tools** (14 tools): DataFrame operations with Arrow IPC data_ref persistence
+  - `read_csv`, `read_parquet`, `read_json` - Load data with chunking support
+  - `to_csv`, `to_parquet` - Export to various formats
+  - `describe`, `head`, `tail` - Data exploration
+  - `filter`, `select`, `groupby`, `join` - Data transformation
+  - `list_data`, `drop_data` - Memory management
+
+- **PostgreSQL MCP Tools** (10 tools): Database operations with asyncpg connection pooling
+  - `pg_connect`, `pg_query`, `pg_execute` - Core database operations
+  - `pg_tables`, `pg_columns`, `pg_schemas` - Schema exploration
+  - `st_tables`, `st_geometry_type`, `st_srid`, `st_extent` - PostGIS spatial support
+
+- **dbt MCP Tools** (8 tools): Build tool wrapper with pre-execution validation
+  - `dbt_parse` - Pre-flight validation (catches dbt 1.9+ deprecations)
+  - `dbt_run`, `dbt_test`, `dbt_build` - Execution with auto-validation
+  - `dbt_compile`, `dbt_ls`, `dbt_docs_generate`, `dbt_lineage` - Analysis tools
+
+- **Commands**: `/ingest`, `/profile`, `/schema`, `/explain`, `/lineage`, `/run`
+- **Agents**: `data-ingestion` (loading/transformation), `data-analysis` (exploration/profiling)
+- **SessionStart Hook**: Graceful PostgreSQL connection check (non-blocking warning)
+
+- **Key Features**:
+  - data_ref system for DataFrame persistence across tool calls
+  - 100k row limit with chunking support for large datasets
+  - Hybrid configuration (system: `~/.config/claude/postgres.env`, project: `.env`)
+  - Auto-detection of dbt projects
+  - Arrow IPC format for efficient memory management
+
+---
+
+## [3.2.0] - 2026-01-24
+
+### Added
+- **git-flow:** `/commit` now detects protected branches before committing
+  - Warns when on protected branch (main, master, development, staging, production)
+  - Offers to create feature branch automatically instead of committing directly
+  - Configurable via `GIT_PROTECTED_BRANCHES` environment variable
+- **netbox:** Platform and primary_ip parameters added to device update tools
+- **claude-config-maintainer:** Auto-enforce mandatory behavior rules via SessionStart hook
+- **scripts:** `release.sh` - Versioning workflow script for consistent releases
+- **scripts:** `verify-hooks.sh` - Verify all hooks are command type
+
+### Changed
+- **doc-guardian:** Hook switched from `prompt` type to `command` type
+  - Prompt hooks unreliable - Claude ignores explicit instructions
+  - New `notify.sh` bash script guarantees exact output behavior
+  - Only notifies for config file changes (commands/, agents/, skills/, hooks/)
+  - Silent exit for all other files - no blocking possible
+- **All hooks:** Converted to command type with stricter plugin prefix enforcement
+  - All hooks now mandate `[plugin-name]` prefix with "NO EXCEPTIONS" rule
+  - Simplified output formats with word limits
+  - Consistent structure across projman, pr-review, code-sentinel, doc-guardian
+- **CLAUDE.md:** Replaced destructive "ALWAYS CLEAR CACHE" rule with "VERIFY AND RESTART"
+  - Cache clearing mid-session breaks MCP tools
+  - Added guidance for proper plugin development workflow
+
+### Fixed
+- **cmdb-assistant:** Complete MCP tool schemas for update operations (#138)
+- **netbox:** Shorten tool names to meet 64-char API limit (#134)
+- **cmdb-assistant:** Correct NetBox API URL format in setup wizard (#132)
+- **gitea/projman:** Type safety for `create_label_smart`, curl-based debug-report (#124)
+- **netbox:** Add diagnostic logging for JSON parse errors (#121)
+- **labels:** Add duplicate check before creating labels (#116)
+- **hooks:** Convert ALL hooks to command type with proper prefixes (#114)
+- Protected branch workflow: Claude no longer commits directly to protected branches (fixes #109)
+- doc-guardian hook no longer blocks workflow (fixes #110)
+
+---
+
 ## [3.1.1] - 2026-01-22
 
 ### Added

CLAUDE.md

@@ -1,18 +1,63 @@
 # CLAUDE.md
 
 This file provides guidance to Claude Code when working with code in this repository.
+## ⛔ MANDATORY BEHAVIOR RULES - READ FIRST
+
+**These rules are NON-NEGOTIABLE. Violating them wastes the user's time and money.**
+
+### 1. WHEN USER ASKS YOU TO CHECK SOMETHING - CHECK EVERYTHING
+- Search ALL locations, not just where you think it is
+- Check cache directories: `~/.claude/plugins/cache/`
+- Check installed: `~/.claude/plugins/marketplaces/`
+- Check source: `~/claude-plugins-work/`
+- **NEVER say "no" or "that's not the issue" without exhaustive verification**
+
+### 2. WHEN USER SAYS SOMETHING IS WRONG - BELIEVE THEM
+- The user knows their system better than you
+- Investigate thoroughly before disagreeing
+- If user suspects cache, CHECK THE CACHE
+- If user suspects a file, READ THE FILE
+- **Your confidence is often wrong. User's instincts are often right.**
+
+### 3. NEVER SAY "DONE" WITHOUT VERIFICATION
+- Run the actual command/script to verify
+- Show the output to the user
+- Check ALL affected locations
+- **"Done" means VERIFIED WORKING, not "I made changes"**
+
+### 4. SHOW EXACTLY WHAT USER ASKS FOR
+- If user asks for messages, show the MESSAGES
+- If user asks for code, show the CODE
+- If user asks for output, show the OUTPUT
+- **Don't interpret or summarize unless asked**
+
+### 5. AFTER PLUGIN UPDATES - VERIFY AND RESTART
+
+**⚠️ DO NOT clear cache mid-session** - this breaks MCP tools that are already loaded.
+
+1. Run `./scripts/verify-hooks.sh` to check hook types
+2. If changes affect MCP servers or hooks, inform the user:
+   > "Plugin changes require a session restart to take effect. Please restart Claude Code."
+3. Cache clearing is ONLY safe **before** starting a new session (not during)
+
+See `docs/DEBUGGING-CHECKLIST.md` for details on cache timing.
+
+**FAILURE TO FOLLOW THESE RULES = WASTED USER TIME = UNACCEPTABLE**
+
+---
+
 
 ## Project Overview
 
 **Repository:** leo-claude-mktplace
-**Version:** 3.0.1
+**Version:** 3.1.2
 **Status:** Production Ready
 
 A plugin marketplace for Claude Code containing:
 
 | Plugin | Description | Version |
 |--------|-------------|---------|
-| `projman` | Sprint planning and project management with Gitea integration | 3.0.0 |
+| `projman` | Sprint planning and project management with Gitea integration | 3.1.0 |
 | `git-flow` | Git workflow automation with smart commits and branch management | 1.0.0 |
 | `pr-review` | Multi-agent PR review with confidence scoring | 1.0.0 |
 | `clarity-assist` | Prompt optimization with ND-friendly accommodations | 1.0.0 |
@@ -59,7 +104,7 @@ leo-claude-mktplace/
 │   │   ├── .claude-plugin/plugin.json
 │   │   ├── .mcp.json
 │   │   ├── mcp-servers/gitea -> ../../../mcp-servers/gitea  # SYMLINK
-│   │   ├── commands/             # 12 commands (incl. setup)
+│   │   ├── commands/             # 13 commands (incl. setup, debug)
 │   │   ├── hooks/                # SessionStart mismatch detection
 │   │   ├── agents/               # 4 agents
 │   │   └── skills/label-taxonomy/
@@ -85,7 +130,9 @@ leo-claude-mktplace/
 │   └── project-hygiene/
 ├── scripts/
 │   ├── setup.sh, post-update.sh
-│   └── validate-marketplace.sh   # Marketplace compliance validation
+│   ├── validate-marketplace.sh   # Marketplace compliance validation
+│   ├── verify-hooks.sh           # Verify all hooks are command type
+│   └── check-venv.sh             # Check MCP server venvs exist
 └── docs/
     ├── CANONICAL-PATHS.md        # Single source of truth for paths
     └── CONFIGURATION.md          # Centralized configuration guide
@@ -132,12 +179,12 @@ leo-claude-mktplace/
 
 | Category | Tools |
 |----------|-------|
-| Issues | `list_issues`, `get_issue`, `create_issue`, `update_issue`, `add_comment` |
-| Labels | `get_labels`, `suggest_labels`, `create_label` |
-| Milestones | `list_milestones`, `get_milestone`, `create_milestone`, `update_milestone` |
-| Dependencies | `list_issue_dependencies`, `create_issue_dependency`, `get_execution_order` |
-| Wiki | `list_wiki_pages`, `get_wiki_page`, `create_wiki_page`, `create_lesson`, `search_lessons` |
-| **Pull Requests** | `list_pull_requests`, `get_pull_request`, `get_pr_diff`, `get_pr_comments`, `create_pr_review`, `add_pr_comment` *(NEW v3.0.0)* |
+| Issues | `list_issues`, `get_issue`, `create_issue`, `update_issue`, `add_comment`, `aggregate_issues` |
+| Labels | `get_labels`, `suggest_labels`, `create_label`, `create_label_smart` |
+| Milestones | `list_milestones`, `get_milestone`, `create_milestone`, `update_milestone`, `delete_milestone` |
+| Dependencies | `list_issue_dependencies`, `create_issue_dependency`, `remove_issue_dependency`, `get_execution_order` |
+| Wiki | `list_wiki_pages`, `get_wiki_page`, `create_wiki_page`, `update_wiki_page`, `create_lesson`, `search_lessons` |
+| **Pull Requests** | `list_pull_requests`, `get_pull_request`, `get_pr_diff`, `get_pr_comments`, `create_pr_review`, `add_pr_comment` |
 | Validation | `validate_repo_org`, `get_branch_protection` |
 
 ### Hybrid Configuration
@@ -246,13 +293,56 @@ See `docs/DEBUGGING-CHECKLIST.md` for systematic troubleshooting.
 - `/debug-report` - Run full diagnostics, create issue if needed
 - `/debug-review` - Investigate and propose fixes
 
-## Versioning Rules
+## Versioning Workflow
 
-- Version displayed ONLY in main `README.md` title: `# Leo Claude Marketplace - vX.Y.Z`
-- `CHANGELOG.md` is authoritative for version history
-- Follow [SemVer](https://semver.org/): MAJOR.MINOR.PATCH
-- On release: Update README title → CHANGELOG → marketplace.json → plugin.json files
+This project follows [SemVer](https://semver.org/) and [Keep a Changelog](https://keepachangelog.com).
+
+### Version Locations (must stay in sync)
+
+| Location | Format | Example |
+|----------|--------|---------|
+| Git tags | `vX.Y.Z` | `v3.2.0` |
+| README.md title | `# Leo Claude Marketplace - vX.Y.Z` | `v3.2.0` |
+| marketplace.json | `"version": "X.Y.Z"` | `3.2.0` |
+| CHANGELOG.md | `## [X.Y.Z] - YYYY-MM-DD` | `[3.2.0] - 2026-01-24` |
+
+### During Development
+
+**All changes go under `[Unreleased]` in CHANGELOG.md.** Never create a versioned section until release time.
+
+```markdown
+## [Unreleased]
+
+### Added
+- New feature description
+
+### Fixed
+- Bug fix description
+```
+
+### Creating a Release
+
+Use the release script to ensure consistency:
+
+```bash
+./scripts/release.sh 3.2.0
+```
+
+The script will:
+1. Validate `[Unreleased]` section has content
+2. Replace `[Unreleased]` with `[3.2.0] - YYYY-MM-DD`
+3. Update README.md title
+4. Update marketplace.json version
+5. Commit and create git tag
+
+### SemVer Guidelines
+
+| Change Type | Version Bump | Example |
+|-------------|--------------|---------|
+| Bug fixes only | PATCH (x.y.**Z**) | 3.1.1 → 3.1.2 |
+| New features (backwards compatible) | MINOR (x.**Y**.0) | 3.1.2 → 3.2.0 |
+| Breaking changes | MAJOR (**X**.0.0) | 3.2.0 → 4.0.0 |
 
 ---
 
-**Last Updated:** 2026-01-22
+**Last Updated:** 2026-01-24

README.md

@@ -1,4 +1,4 @@
-# Leo Claude Marketplace - v3.1.1
+# Leo Claude Marketplace - v4.0.0
 
 A collection of Claude Code plugins for project management, infrastructure automation, and development workflows.
 
@@ -19,7 +19,7 @@ AI-guided sprint planning with full Gitea integration. Transforms a proven 15-sp
 - Branch-aware security (development/staging/production)
 - Pre-sprint-close code quality review and test verification
 
-**Commands:** `/sprint-plan`, `/sprint-start`, `/sprint-status`, `/sprint-close`, `/labels-sync`, `/initial-setup`, `/project-init`, `/project-sync`, `/review`, `/test-check`, `/test-gen`
+**Commands:** `/sprint-plan`, `/sprint-start`, `/sprint-status`, `/sprint-close`, `/labels-sync`, `/initial-setup`, `/project-init`, `/project-sync`, `/review`, `/test-check`, `/test-gen`, `/debug-report`, `/debug-review`
 
 #### [git-flow](./plugins/git-flow/README.md) *NEW in v3.0.0*
 **Git Workflow Automation**
@@ -96,6 +96,21 @@ Full CRUD operations for network infrastructure management directly from Claude
 
 **Commands:** `/initial-setup`, `/cmdb-search`, `/cmdb-device`, `/cmdb-ip`, `/cmdb-site`
 
+### Data Engineering
+
+#### [data-platform](./plugins/data-platform/README.md) *NEW*
+**pandas, PostgreSQL/PostGIS, and dbt Integration**
+
+Comprehensive data engineering toolkit with persistent DataFrame storage.
+
+- 14 pandas tools with Arrow IPC data_ref system
+- 10 PostgreSQL/PostGIS tools with connection pooling
+- 8 dbt tools with automatic pre-validation
+- 100k row limit with chunking support
+- Auto-detection of dbt projects
+
+**Commands:** `/ingest`, `/profile`, `/schema`, `/explain`, `/lineage`, `/run`
+
 ## MCP Servers
 
 MCP servers are **shared at repository root** with **symlinks** from plugins that use them.
@@ -106,11 +121,11 @@ Full Gitea API integration for project management.
 
 | Category | Tools |
 |----------|-------|
-| Issues | `list_issues`, `get_issue`, `create_issue`, `update_issue`, `add_comment` |
-| Labels | `get_labels`, `suggest_labels`, `create_label` |
-| Wiki | `list_wiki_pages`, `get_wiki_page`, `create_wiki_page`, `create_lesson`, `search_lessons` |
-| Milestones | `list_milestones`, `get_milestone`, `create_milestone`, `update_milestone` |
-| Dependencies | `list_issue_dependencies`, `create_issue_dependency`, `get_execution_order` |
+| Issues | `list_issues`, `get_issue`, `create_issue`, `update_issue`, `add_comment`, `aggregate_issues` |
+| Labels | `get_labels`, `suggest_labels`, `create_label`, `create_label_smart` |
+| Wiki | `list_wiki_pages`, `get_wiki_page`, `create_wiki_page`, `update_wiki_page`, `create_lesson`, `search_lessons` |
+| Milestones | `list_milestones`, `get_milestone`, `create_milestone`, `update_milestone`, `delete_milestone` |
+| Dependencies | `list_issue_dependencies`, `create_issue_dependency`, `remove_issue_dependency`, `get_execution_order` |
 | **Pull Requests** | `list_pull_requests`, `get_pull_request`, `get_pr_diff`, `get_pr_comments`, `create_pr_review`, `add_pr_comment` *(NEW in v3.0.0)* |
 | Validation | `validate_repo_org`, `get_branch_protection` |
 
@@ -126,6 +141,17 @@ Comprehensive NetBox REST API integration for infrastructure management.
 | Virtualization | Clusters, VMs, Interfaces |
 | Extras | Tags, Custom Fields, Audit Log |
 
+### Data Platform MCP Server (shared) *NEW*
+
+pandas, PostgreSQL/PostGIS, and dbt integration for data engineering.
+
+| Category | Tools |
+|----------|-------|
+| pandas | `read_csv`, `read_parquet`, `read_json`, `to_csv`, `to_parquet`, `describe`, `head`, `tail`, `filter`, `select`, `groupby`, `join`, `list_data`, `drop_data` |
+| PostgreSQL | `pg_connect`, `pg_query`, `pg_execute`, `pg_tables`, `pg_columns`, `pg_schemas` |
+| PostGIS | `st_tables`, `st_geometry_type`, `st_srid`, `st_extent` |
+| dbt | `dbt_parse`, `dbt_run`, `dbt_test`, `dbt_build`, `dbt_compile`, `dbt_ls`, `dbt_docs_generate`, `dbt_lineage` |
+
 ## Installation
 
 ### Prerequisites
@@ -222,6 +248,7 @@ After installing plugins, the `/plugin` command may show `(no content)` - this i
 | code-sentinel | `/code-sentinel:security-scan` |
 | claude-config-maintainer | `/claude-config-maintainer:config-analyze` |
 | cmdb-assistant | `/cmdb-assistant:cmdb-search` |
+| data-platform | `/data-platform:ingest` |
 
 ## Repository Structure
 
@@ -231,12 +258,14 @@ leo-claude-mktplace/
 │   └── marketplace.json
 ├── mcp-servers/                   # SHARED MCP servers (v3.0.0+)
 │   ├── gitea/                     # Gitea MCP (issues, PRs, wiki)
-│   └── netbox/                    # NetBox MCP (CMDB)
+│   ├── netbox/                    # NetBox MCP (CMDB)
+│   └── data-platform/             # Data engineering (pandas, PostgreSQL, dbt)
 ├── plugins/                       # All plugins
 │   ├── projman/                   # Sprint management
-│   ├── git-flow/                  # Git workflow automation (NEW)
-│   ├── pr-review/                 # PR review (NEW)
-│   ├── clarity-assist/            # Prompt optimization (NEW)
+│   ├── git-flow/                  # Git workflow automation
+│   ├── pr-review/                 # PR review
+│   ├── clarity-assist/            # Prompt optimization
+│   ├── data-platform/             # Data engineering (NEW)
 │   ├── claude-config-maintainer/  # CLAUDE.md optimization
 │   ├── cmdb-assistant/            # NetBox CMDB integration
 │   ├── doc-guardian/              # Documentation drift detection
@@ -245,7 +274,8 @@ leo-claude-mktplace/
 ├── docs/                          # Documentation
 │   ├── CANONICAL-PATHS.md         # Path reference
 │   └── CONFIGURATION.md           # Setup guide
-└── scripts/                       # Setup scripts
+├── scripts/                       # Setup scripts
+└── CHANGELOG.md                   # Version history
 ```
 
 ## Documentation
@@ -257,6 +287,7 @@ leo-claude-mktplace/
 | [COMMANDS-CHEATSHEET.md](./docs/COMMANDS-CHEATSHEET.md) | All commands quick reference |
 | [UPDATING.md](./docs/UPDATING.md) | Update guide for the marketplace |
 | [CANONICAL-PATHS.md](./docs/CANONICAL-PATHS.md) | Authoritative path reference |
+| [DEBUGGING-CHECKLIST.md](./docs/DEBUGGING-CHECKLIST.md) | Systematic troubleshooting guide |
 | [CHANGELOG.md](./CHANGELOG.md) | Version history |
 
 ## License

docs/CANONICAL-PATHS.md

@@ -2,7 +2,7 @@
 
 **This file defines ALL valid paths in this repository. No exceptions. No inference. No assumptions.**
 
-Last Updated: 2026-01-20 (v3.0.0)
+Last Updated: 2026-01-23 (v3.1.2)
 
 ---
 
@@ -17,10 +17,10 @@ leo-claude-mktplace/
 ├── docs/                       # All documentation
 │   ├── architecture/           # Draw.io diagrams and specs
 │   ├── CANONICAL-PATHS.md      # This file - single source of truth
+│   ├── COMMANDS-CHEATSHEET.md  # All commands quick reference
 │   ├── CONFIGURATION.md        # Centralized configuration guide
 │   ├── DEBUGGING-CHECKLIST.md  # Systematic troubleshooting guide
-│   ├── UPDATING.md             # Update guide
-│   └── workflows/              # Workflow documentation
+│   └── UPDATING.md             # Update guide
 ├── hooks/                      # Shared hooks (if any)
 ├── mcp-servers/                # SHARED MCP servers (v3.0.0+)
 │   ├── gitea/                  # Gitea MCP server
@@ -156,7 +156,6 @@ The symlink target is relative: `../../../mcp-servers/{server}`
 | Type | Location |
 |------|----------|
 | Architecture diagrams | `docs/architecture/` |
-| Workflow docs | `docs/workflows/` |
 | This file | `docs/CANONICAL-PATHS.md` |
 | Update guide | `docs/UPDATING.md` |
 | Configuration guide | `docs/CONFIGURATION.md` |

docs/DEBUGGING-CHECKLIST.md

@@ -197,6 +197,51 @@ echo -e "\n=== Config Files ==="
 
 ---
 
+## Cache Clearing: When It's Safe vs Destructive
+
+**⚠️ CRITICAL: Never clear plugin cache mid-session.**
+
+### Why Cache Clearing Breaks MCP Tools
+
+When Claude Code starts a session:
+1. MCP tools are loaded from the cache directory
+2. Tool definitions include **absolute paths** to the venv (e.g., `~/.claude/plugins/cache/.../venv/`)
+3. These paths are cached in the session memory
+4. Deleting the cache removes the venv, but the session still references the old paths
+5. Any MCP tool making HTTP requests fails with TLS certificate errors
+
+### When Cache Clearing is SAFE
+
+| Scenario | Safe? | Action |
+|----------|-------|--------|
+| Before starting Claude Code | ✅ Yes | Clear cache, then start session |
+| Between sessions | ✅ Yes | Clear cache after `/exit`, before next session |
+| During a session | ❌ NO | Never - will break MCP tools |
+| After plugin source edits | ❌ NO | Restart session instead |
+
+### Recovery: MCP Tools Broken Mid-Session
+
+If you accidentally cleared cache during a session and MCP tools fail:
+
+```
+Error: Could not find a suitable TLS CA certificate bundle, invalid path:
+/home/.../.claude/plugins/cache/.../certifi/cacert.pem
+```
+
+**Fix:**
+1. Exit the current session (`/exit` or Ctrl+C)
+2. Start a new Claude Code session
+3. MCP tools will reload from the reinstalled cache
+
+### Correct Workflow for Plugin Development
+
+1. Make changes to plugin source files
+2. Run `./scripts/verify-hooks.sh` (verifies hook types)
+3. Tell user: "Please restart Claude Code for changes to take effect"
+4. **Do NOT clear cache** - session restart handles reloading
+
+---
+
 ## Automated Diagnostics
 
 Use these commands for automated checking:

mcp-servers/data-platform/README.md

@@ -0,0 +1,131 @@
+# Data Platform MCP Server
+
+MCP Server providing pandas, PostgreSQL/PostGIS, and dbt tools for Claude Code.
+
+## Features
+
+- **pandas Tools**: DataFrame operations with Arrow IPC data_ref persistence
+- **PostgreSQL Tools**: Database queries with asyncpg connection pooling
+- **PostGIS Tools**: Spatial data operations
+- **dbt Tools**: Build tool wrapper with pre-execution validation
+
+## Installation
+
+```bash
+cd mcp-servers/data-platform
+python -m venv .venv
+source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+pip install -r requirements.txt
+```
+
+## Configuration
+
+### System-Level (PostgreSQL credentials)
+
+Create `~/.config/claude/postgres.env`:
+
+```env
+POSTGRES_URL=postgresql://user:password@host:5432/database
+```
+
+### Project-Level (dbt paths)
+
+Create `.env` in your project root:
+
+```env
+DBT_PROJECT_DIR=/path/to/dbt/project
+DBT_PROFILES_DIR=/path/to/.dbt
+DATA_PLATFORM_MAX_ROWS=100000
+```
+
+## Tools
+
+### pandas Tools (14 tools)
+
+| Tool | Description |
+|------|-------------|
+| `read_csv` | Load CSV file into DataFrame |
+| `read_parquet` | Load Parquet file into DataFrame |
+| `read_json` | Load JSON/JSONL file into DataFrame |
+| `to_csv` | Export DataFrame to CSV file |
+| `to_parquet` | Export DataFrame to Parquet file |
+| `describe` | Get statistical summary of DataFrame |
+| `head` | Get first N rows of DataFrame |
+| `tail` | Get last N rows of DataFrame |
+| `filter` | Filter DataFrame rows by condition |
+| `select` | Select specific columns from DataFrame |
+| `groupby` | Group DataFrame and aggregate |
+| `join` | Join two DataFrames |
+| `list_data` | List all stored DataFrames |
+| `drop_data` | Remove a DataFrame from storage |
+
+### PostgreSQL Tools (6 tools)
+
+| Tool | Description |
+|------|-------------|
+| `pg_connect` | Test connection and return status |
+| `pg_query` | Execute SELECT, return as data_ref |
+| `pg_execute` | Execute INSERT/UPDATE/DELETE |
+| `pg_tables` | List all tables in schema |
+| `pg_columns` | Get column info for table |
+| `pg_schemas` | List all schemas |
+
+### PostGIS Tools (4 tools)
+
+| Tool | Description |
+|------|-------------|
+| `st_tables` | List PostGIS-enabled tables |
+| `st_geometry_type` | Get geometry type of column |
+| `st_srid` | Get SRID of geometry column |
+| `st_extent` | Get bounding box of geometries |
+
+### dbt Tools (8 tools)
+
+| Tool | Description |
+|------|-------------|
+| `dbt_parse` | Validate project (pre-execution) |
+| `dbt_run` | Run models with selection |
+| `dbt_test` | Run tests |
+| `dbt_build` | Run + test |
+| `dbt_compile` | Compile SQL without executing |
+| `dbt_ls` | List resources |
+| `dbt_docs_generate` | Generate documentation |
+| `dbt_lineage` | Get model dependencies |
+
+## data_ref System
+
+All DataFrame operations use a `data_ref` system to persist data across tool calls:
+
+1. **Load data**: Returns a `data_ref` string (e.g., `"df_a1b2c3d4"`)
+2. **Use data_ref**: Pass to other tools (filter, join, export)
+3. **List data**: Use `list_data` to see all stored DataFrames
+4. **Clean up**: Use `drop_data` when done
+
+### Example Flow
+
+```
+read_csv("data.csv") → {"data_ref": "sales_data", "rows": 1000}
+filter("sales_data", "amount > 100") → {"data_ref": "sales_data_filtered"}
+describe("sales_data_filtered") → {statistics}
+to_parquet("sales_data_filtered", "output.parquet") → {success}
+```
+
+## Memory Management
+
+- Default row limit: 100,000 rows per DataFrame
+- Configure via `DATA_PLATFORM_MAX_ROWS` environment variable
+- Use chunked processing for large files (`chunk_size` parameter)
+- Monitor with `list_data` tool (shows memory usage)
+
+## Running
+
+```bash
+python -m mcp_server.server
+```
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest
+```

mcp-servers/data-platform/mcp_server/__init__.py

@@ -0,0 +1,7 @@
+"""
+Data Platform MCP Server.
+
+Provides pandas, PostgreSQL/PostGIS, and dbt tools to Claude Code via MCP.
+"""
+
+__version__ = "1.0.0"

mcp-servers/data-platform/mcp_server/config.py

@@ -0,0 +1,195 @@
+"""
+Configuration loader for Data Platform MCP Server.
+
+Implements hybrid configuration system:
+- System-level: ~/.config/claude/postgres.env (credentials)
+- Project-level: .env (dbt project paths, overrides)
+- Auto-detection: dbt_project.yml discovery
+"""
+from pathlib import Path
+from dotenv import load_dotenv
+import os
+import logging
+from typing import Dict, Optional
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+class DataPlatformConfig:
+    """Hybrid configuration loader for data platform tools"""
+
+    def __init__(self):
+        self.postgres_url: Optional[str] = None
+        self.dbt_project_dir: Optional[str] = None
+        self.dbt_profiles_dir: Optional[str] = None
+        self.max_rows: int = 100_000
+
+    def load(self) -> Dict[str, Optional[str]]:
+        """
+        Load configuration from system and project levels.
+
+        Returns:
+            Dict containing postgres_url, dbt_project_dir, dbt_profiles_dir, max_rows
+
+        Note:
+            PostgreSQL credentials are optional - server can run in pandas-only mode.
+        """
+        # Load system config (PostgreSQL credentials)
+        system_config = Path.home() / '.config' / 'claude' / 'postgres.env'
+        if system_config.exists():
+            load_dotenv(system_config)
+            logger.info(f"Loaded system configuration from {system_config}")
+        else:
+            logger.info(
+                f"System config not found: {system_config} - "
+                "PostgreSQL tools will be unavailable"
+            )
+
+        # Find project directory
+        project_dir = self._find_project_directory()
+
+        # Load project config (overrides system)
+        if project_dir:
+            project_config = project_dir / '.env'
+            if project_config.exists():
+                load_dotenv(project_config, override=True)
+                logger.info(f"Loaded project configuration from {project_config}")
+
+        # Extract values
+        self.postgres_url = os.getenv('POSTGRES_URL')
+        self.dbt_project_dir = os.getenv('DBT_PROJECT_DIR')
+        self.dbt_profiles_dir = os.getenv('DBT_PROFILES_DIR')
+        self.max_rows = int(os.getenv('DATA_PLATFORM_MAX_ROWS', '100000'))
+
+        # Auto-detect dbt project if not specified
+        if not self.dbt_project_dir and project_dir:
+            self.dbt_project_dir = self._find_dbt_project(project_dir)
+            if self.dbt_project_dir:
+                logger.info(f"Auto-detected dbt project: {self.dbt_project_dir}")
+
+        # Default dbt profiles dir to ~/.dbt
+        if not self.dbt_profiles_dir:
+            default_profiles = Path.home() / '.dbt'
+            if default_profiles.exists():
+                self.dbt_profiles_dir = str(default_profiles)
+
+        return {
+            'postgres_url': self.postgres_url,
+            'dbt_project_dir': self.dbt_project_dir,
+            'dbt_profiles_dir': self.dbt_profiles_dir,
+            'max_rows': self.max_rows,
+            'postgres_available': self.postgres_url is not None,
+            'dbt_available': self.dbt_project_dir is not None
+        }
+
+    def _find_project_directory(self) -> Optional[Path]:
+        """
+        Find the user's project directory.
+
+        Returns:
+            Path to project directory, or None if not found
+        """
+        # Strategy 1: Check CLAUDE_PROJECT_DIR environment variable
+        project_dir = os.getenv('CLAUDE_PROJECT_DIR')
+        if project_dir:
+            path = Path(project_dir)
+            if path.exists():
+                logger.info(f"Found project directory from CLAUDE_PROJECT_DIR: {path}")
+                return path
+
+        # Strategy 2: Check PWD
+        pwd = os.getenv('PWD')
+        if pwd:
+            path = Path(pwd)
+            if path.exists() and (
+                (path / '.git').exists() or
+                (path / '.env').exists() or
+                (path / 'dbt_project.yml').exists()
+            ):
+                logger.info(f"Found project directory from PWD: {path}")
+                return path
+
+        # Strategy 3: Check current working directory
+        cwd = Path.cwd()
+        if (cwd / '.git').exists() or (cwd / '.env').exists() or (cwd / 'dbt_project.yml').exists():
+            logger.info(f"Found project directory from cwd: {cwd}")
+            return cwd
+
+        logger.debug("Could not determine project directory")
+        return None
+
+    def _find_dbt_project(self, start_dir: Path) -> Optional[str]:
+        """
+        Find dbt_project.yml in the project or its subdirectories.
+
+        Args:
+            start_dir: Directory to start searching from
+
+        Returns:
+            Path to dbt project directory, or None if not found
+        """
+        # Check root
+        if (start_dir / 'dbt_project.yml').exists():
+            return str(start_dir)
+
+        # Check common subdirectories
+        for subdir in ['dbt', 'transform', 'analytics', 'models']:
+            candidate = start_dir / subdir
+            if (candidate / 'dbt_project.yml').exists():
+                return str(candidate)
+
+        # Search one level deep
+        for item in start_dir.iterdir():
+            if item.is_dir() and not item.name.startswith('.'):
+                if (item / 'dbt_project.yml').exists():
+                    return str(item)
+
+        return None
+
+
+def load_config() -> Dict[str, Optional[str]]:
+    """
+    Convenience function to load configuration.
+
+    Returns:
+        Configuration dictionary
+    """
+    config = DataPlatformConfig()
+    return config.load()
+
+
+def check_postgres_connection() -> Dict[str, any]:
+    """
+    Check PostgreSQL connection status for SessionStart hook.
+
+    Returns:
+        Dict with connection status and message
+    """
+    import asyncio
+
+    config = load_config()
+    if not config.get('postgres_url'):
+        return {
+            'connected': False,
+            'message': 'PostgreSQL not configured (POSTGRES_URL not set)'
+        }
+
+    async def test_connection():
+        try:
+            import asyncpg
+            conn = await asyncpg.connect(config['postgres_url'], timeout=5)
+            version = await conn.fetchval('SELECT version()')
+            await conn.close()
+            return {
+                'connected': True,
+                'message': f'Connected to PostgreSQL',
+                'version': version.split(',')[0] if version else 'Unknown'
+            }
+        except Exception as e:
+            return {
+                'connected': False,
+                'message': f'PostgreSQL connection failed: {str(e)}'
+            }
+
+    return asyncio.run(test_connection())

mcp-servers/data-platform/mcp_server/data_store.py

@@ -0,0 +1,219 @@
+"""
+Arrow IPC DataFrame Registry.
+
+Provides persistent storage for DataFrames across tool calls using Apache Arrow
+for efficient memory management and serialization.
+"""
+import pyarrow as pa
+import pandas as pd
+import uuid
+import logging
+from typing import Dict, Optional, List, Union
+from dataclasses import dataclass
+from datetime import datetime
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class DataFrameInfo:
+    """Metadata about a stored DataFrame"""
+    ref: str
+    rows: int
+    columns: int
+    column_names: List[str]
+    dtypes: Dict[str, str]
+    memory_bytes: int
+    created_at: datetime
+    source: Optional[str] = None
+
+
+class DataStore:
+    """
+    Singleton registry for Arrow Tables (DataFrames).
+
+    Uses Arrow IPC format for efficient memory usage and supports
+    data_ref based retrieval across multiple tool calls.
+    """
+    _instance = None
+    _dataframes: Dict[str, pa.Table] = {}
+    _metadata: Dict[str, DataFrameInfo] = {}
+    _max_rows: int = 100_000
+
+    def __new__(cls):
+        if cls._instance is None:
+            cls._instance = super().__new__(cls)
+            cls._dataframes = {}
+            cls._metadata = {}
+        return cls._instance
+
+    @classmethod
+    def get_instance(cls) -> 'DataStore':
+        """Get the singleton instance"""
+        if cls._instance is None:
+            cls._instance = cls()
+        return cls._instance
+
+    @classmethod
+    def set_max_rows(cls, max_rows: int):
+        """Set the maximum rows limit"""
+        cls._max_rows = max_rows
+
+    def store(
+        self,
+        data: Union[pa.Table, pd.DataFrame],
+        name: Optional[str] = None,
+        source: Optional[str] = None
+    ) -> str:
+        """
+        Store a DataFrame and return its reference.
+
+        Args:
+            data: Arrow Table or pandas DataFrame
+            name: Optional name for the reference (auto-generated if not provided)
+            source: Optional source description (e.g., file path, query)
+
+        Returns:
+            data_ref string to retrieve the DataFrame later
+        """
+        # Convert pandas to Arrow if needed
+        if isinstance(data, pd.DataFrame):
+            table = pa.Table.from_pandas(data)
+        else:
+            table = data
+
+        # Generate reference
+        data_ref = name or f"df_{uuid.uuid4().hex[:8]}"
+
+        # Ensure unique reference
+        if data_ref in self._dataframes and name is None:
+            data_ref = f"{data_ref}_{uuid.uuid4().hex[:4]}"
+
+        # Store table
+        self._dataframes[data_ref] = table
+
+        # Store metadata
+        schema = table.schema
+        self._metadata[data_ref] = DataFrameInfo(
+            ref=data_ref,
+            rows=table.num_rows,
+            columns=table.num_columns,
+            column_names=[f.name for f in schema],
+            dtypes={f.name: str(f.type) for f in schema},
+            memory_bytes=table.nbytes,
+            created_at=datetime.now(),
+            source=source
+        )
+
+        logger.info(f"Stored DataFrame '{data_ref}': {table.num_rows} rows, {table.num_columns} cols")
+        return data_ref
+
+    def get(self, data_ref: str) -> Optional[pa.Table]:
+        """
+        Retrieve an Arrow Table by reference.
+
+        Args:
+            data_ref: Reference string from store()
+
+        Returns:
+            Arrow Table or None if not found
+        """
+        return self._dataframes.get(data_ref)
+
+    def get_pandas(self, data_ref: str) -> Optional[pd.DataFrame]:
+        """
+        Retrieve a DataFrame as pandas.
+
+        Args:
+            data_ref: Reference string from store()
+
+        Returns:
+            pandas DataFrame or None if not found
+        """
+        table = self.get(data_ref)
+        if table is not None:
+            return table.to_pandas()
+        return None
+
+    def get_info(self, data_ref: str) -> Optional[DataFrameInfo]:
+        """
+        Get metadata about a stored DataFrame.
+
+        Args:
+            data_ref: Reference string
+
+        Returns:
+            DataFrameInfo or None if not found
+        """
+        return self._metadata.get(data_ref)
+
+    def list_refs(self) -> List[Dict]:
+        """
+        List all stored DataFrame references with metadata.
+
+        Returns:
+            List of dicts with ref, rows, columns, memory info
+        """
+        result = []
+        for ref, info in self._metadata.items():
+            result.append({
+                'ref': ref,
+                'rows': info.rows,
+                'columns': info.columns,
+                'column_names': info.column_names,
+                'memory_mb': round(info.memory_bytes / (1024 * 1024), 2),
+                'source': info.source,
+                'created_at': info.created_at.isoformat()
+            })
+        return result
+
+    def drop(self, data_ref: str) -> bool:
+        """
+        Remove a DataFrame from the store.
+
+        Args:
+            data_ref: Reference string
+
+        Returns:
+            True if removed, False if not found
+        """
+        if data_ref in self._dataframes:
+            del self._dataframes[data_ref]
+            del self._metadata[data_ref]
+            logger.info(f"Dropped DataFrame '{data_ref}'")
+            return True
+        return False
+
+    def clear(self):
+        """Remove all stored DataFrames"""
+        count = len(self._dataframes)
+        self._dataframes.clear()
+        self._metadata.clear()
+        logger.info(f"Cleared {count} DataFrames from store")
+
+    def total_memory_bytes(self) -> int:
+        """Get total memory used by all stored DataFrames"""
+        return sum(info.memory_bytes for info in self._metadata.values())
+
+    def total_memory_mb(self) -> float:
+        """Get total memory in MB"""
+        return round(self.total_memory_bytes() / (1024 * 1024), 2)
+
+    def check_row_limit(self, row_count: int) -> Dict:
+        """
+        Check if row count exceeds limit.
+
+        Args:
+            row_count: Number of rows
+
+        Returns:
+            Dict with 'exceeded' bool and 'message' if exceeded
+        """
+        if row_count > self._max_rows:
+            return {
+                'exceeded': True,
+                'message': f"Row count ({row_count:,}) exceeds limit ({self._max_rows:,})",
+                'suggestion': f"Use chunked processing or filter data first",
+                'limit': self._max_rows
+            }
+        return {'exceeded': False}

mcp-servers/data-platform/mcp_server/dbt_tools.py

@@ -0,0 +1,387 @@
+"""
+dbt MCP Tools.
+
+Provides dbt CLI wrapper with pre-execution validation.
+"""
+import subprocess
+import json
+import logging
+import os
+from pathlib import Path
+from typing import Dict, List, Optional, Any
+
+from .config import load_config
+
+logger = logging.getLogger(__name__)
+
+
+class DbtTools:
+    """dbt CLI wrapper tools with pre-validation"""
+
+    def __init__(self):
+        self.config = load_config()
+        self.project_dir = self.config.get('dbt_project_dir')
+        self.profiles_dir = self.config.get('dbt_profiles_dir')
+
+    def _get_dbt_command(self, cmd: List[str]) -> List[str]:
+        """Build dbt command with project and profiles directories"""
+        base = ['dbt']
+        if self.project_dir:
+            base.extend(['--project-dir', self.project_dir])
+        if self.profiles_dir:
+            base.extend(['--profiles-dir', self.profiles_dir])
+        base.extend(cmd)
+        return base
+
+    def _run_dbt(
+        self,
+        cmd: List[str],
+        timeout: int = 300,
+        capture_json: bool = False
+    ) -> Dict:
+        """
+        Run dbt command and return result.
+
+        Args:
+            cmd: dbt subcommand and arguments
+            timeout: Command timeout in seconds
+            capture_json: If True, parse JSON output
+
+        Returns:
+            Dict with command result
+        """
+        if not self.project_dir:
+            return {
+                'error': 'dbt project not found',
+                'suggestion': 'Set DBT_PROJECT_DIR in project .env or ensure dbt_project.yml exists'
+            }
+
+        full_cmd = self._get_dbt_command(cmd)
+        logger.info(f"Running: {' '.join(full_cmd)}")
+
+        try:
+            env = os.environ.copy()
+            # Disable dbt analytics/tracking
+            env['DBT_SEND_ANONYMOUS_USAGE_STATS'] = 'false'
+
+            result = subprocess.run(
+                full_cmd,
+                capture_output=True,
+                text=True,
+                timeout=timeout,
+                cwd=self.project_dir,
+                env=env
+            )
+
+            output = {
+                'success': result.returncode == 0,
+                'command': ' '.join(cmd),
+                'stdout': result.stdout,
+                'stderr': result.stderr if result.returncode != 0 else None
+            }
+
+            if capture_json and result.returncode == 0:
+                try:
+                    output['data'] = json.loads(result.stdout)
+                except json.JSONDecodeError:
+                    pass
+
+            return output
+
+        except subprocess.TimeoutExpired:
+            return {
+                'error': f'Command timed out after {timeout}s',
+                'command': ' '.join(cmd)
+            }
+        except FileNotFoundError:
+            return {
+                'error': 'dbt not found in PATH',
+                'suggestion': 'Install dbt: pip install dbt-core dbt-postgres'
+            }
+        except Exception as e:
+            logger.error(f"dbt command failed: {e}")
+            return {'error': str(e)}
+
+    async def dbt_parse(self) -> Dict:
+        """
+        Validate dbt project without executing (pre-flight check).
+
+        Returns:
+            Dict with validation result and any errors
+        """
+        result = self._run_dbt(['parse'])
+
+        # Check if _run_dbt returned an error (e.g., project not found, timeout, dbt not installed)
+        if 'error' in result:
+            return result
+
+        if not result.get('success'):
+            # Extract useful error info from stderr
+            stderr = result.get('stderr', '') or result.get('stdout', '')
+            errors = []
+
+            # Look for common dbt 1.9+ deprecation warnings
+            if 'deprecated' in stderr.lower():
+                errors.append({
+                    'type': 'deprecation',
+                    'message': 'Deprecated syntax found - check dbt 1.9+ migration guide'
+                })
+
+            # Look for compilation errors
+            if 'compilation error' in stderr.lower():
+                errors.append({
+                    'type': 'compilation',
+                    'message': 'SQL compilation error - check model syntax'
+                })
+
+            return {
+                'valid': False,
+                'errors': errors,
+                'details': stderr[:2000] if stderr else None,
+                'suggestion': 'Fix issues before running dbt models'
+            }
+
+        return {
+            'valid': True,
+            'message': 'dbt project validation passed'
+        }
+
+    async def dbt_run(
+        self,
+        select: Optional[str] = None,
+        exclude: Optional[str] = None,
+        full_refresh: bool = False
+    ) -> Dict:
+        """
+        Run dbt models with pre-validation.
+
+        Args:
+            select: Model selection (e.g., "model_name", "+model_name", "tag:daily")
+            exclude: Models to exclude
+            full_refresh: If True, rebuild incremental models
+
+        Returns:
+            Dict with run result
+        """
+        # ALWAYS validate first
+        parse_result = await self.dbt_parse()
+        if not parse_result.get('valid'):
+            return {
+                'error': 'Pre-validation failed',
+                **parse_result
+            }
+
+        cmd = ['run']
+        if select:
+            cmd.extend(['--select', select])
+        if exclude:
+            cmd.extend(['--exclude', exclude])
+        if full_refresh:
+            cmd.append('--full-refresh')
+
+        return self._run_dbt(cmd)
+
+    async def dbt_test(
+        self,
+        select: Optional[str] = None,
+        exclude: Optional[str] = None
+    ) -> Dict:
+        """
+        Run dbt tests.
+
+        Args:
+            select: Test selection
+            exclude: Tests to exclude
+
+        Returns:
+            Dict with test results
+        """
+        cmd = ['test']
+        if select:
+            cmd.extend(['--select', select])
+        if exclude:
+            cmd.extend(['--exclude', exclude])
+
+        return self._run_dbt(cmd)
+
+    async def dbt_build(
+        self,
+        select: Optional[str] = None,
+        exclude: Optional[str] = None,
+        full_refresh: bool = False
+    ) -> Dict:
+        """
+        Run dbt build (run + test) with pre-validation.
+
+        Args:
+            select: Model/test selection
+            exclude: Resources to exclude
+            full_refresh: If True, rebuild incremental models
+
+        Returns:
+            Dict with build result
+        """
+        # ALWAYS validate first
+        parse_result = await self.dbt_parse()
+        if not parse_result.get('valid'):
+            return {
+                'error': 'Pre-validation failed',
+                **parse_result
+            }
+
+        cmd = ['build']
+        if select:
+            cmd.extend(['--select', select])
+        if exclude:
+            cmd.extend(['--exclude', exclude])
+        if full_refresh:
+            cmd.append('--full-refresh')
+
+        return self._run_dbt(cmd)
+
+    async def dbt_compile(
+        self,
+        select: Optional[str] = None
+    ) -> Dict:
+        """
+        Compile dbt models to SQL without executing.
+
+        Args:
+            select: Model selection
+
+        Returns:
+            Dict with compiled SQL info
+        """
+        cmd = ['compile']
+        if select:
+            cmd.extend(['--select', select])
+
+        return self._run_dbt(cmd)
+
+    async def dbt_ls(
+        self,
+        select: Optional[str] = None,
+        resource_type: Optional[str] = None,
+        output: str = 'name'
+    ) -> Dict:
+        """
+        List dbt resources.
+
+        Args:
+            select: Resource selection
+            resource_type: Filter by type (model, test, seed, snapshot, source)
+            output: Output format ('name', 'path', 'json')
+
+        Returns:
+            Dict with list of resources
+        """
+        cmd = ['ls', '--output', output]
+        if select:
+            cmd.extend(['--select', select])
+        if resource_type:
+            cmd.extend(['--resource-type', resource_type])
+
+        result = self._run_dbt(cmd)
+
+        if result.get('success') and result.get('stdout'):
+            lines = [l.strip() for l in result['stdout'].split('\n') if l.strip()]
+            result['resources'] = lines
+            result['count'] = len(lines)
+
+        return result
+
+    async def dbt_docs_generate(self) -> Dict:
+        """
+        Generate dbt documentation.
+
+        Returns:
+            Dict with generation result
+        """
+        result = self._run_dbt(['docs', 'generate'])
+
+        if result.get('success') and self.project_dir:
+            # Check for generated catalog
+            catalog_path = Path(self.project_dir) / 'target' / 'catalog.json'
+            manifest_path = Path(self.project_dir) / 'target' / 'manifest.json'
+            result['catalog_generated'] = catalog_path.exists()
+            result['manifest_generated'] = manifest_path.exists()
+
+        return result
+
+    async def dbt_lineage(self, model: str) -> Dict:
+        """
+        Get model dependencies and lineage.
+
+        Args:
+            model: Model name to analyze
+
+        Returns:
+            Dict with upstream and downstream dependencies
+        """
+        if not self.project_dir:
+            return {'error': 'dbt project not found'}
+
+        manifest_path = Path(self.project_dir) / 'target' / 'manifest.json'
+
+        # Generate manifest if not exists
+        if not manifest_path.exists():
+            compile_result = await self.dbt_compile(select=model)
+            if not compile_result.get('success'):
+                return {
+                    'error': 'Failed to compile manifest',
+                    'details': compile_result
+                }
+
+        if not manifest_path.exists():
+            return {
+                'error': 'Manifest not found',
+                'suggestion': 'Run dbt compile first'
+            }
+
+        try:
+            with open(manifest_path) as f:
+                manifest = json.load(f)
+
+            # Find the model node
+            model_key = None
+            for key in manifest.get('nodes', {}):
+                if key.endswith(f'.{model}') or manifest['nodes'][key].get('name') == model:
+                    model_key = key
+                    break
+
+            if not model_key:
+                return {
+                    'error': f'Model not found: {model}',
+                    'available_models': [
+                        n.get('name') for n in manifest.get('nodes', {}).values()
+                        if n.get('resource_type') == 'model'
+                    ][:20]
+                }
+
+            node = manifest['nodes'][model_key]
+
+            # Get upstream (depends_on)
+            upstream = node.get('depends_on', {}).get('nodes', [])
+
+            # Get downstream (find nodes that depend on this one)
+            downstream = []
+            for key, other_node in manifest.get('nodes', {}).items():
+                deps = other_node.get('depends_on', {}).get('nodes', [])
+                if model_key in deps:
+                    downstream.append(key)
+
+            return {
+                'model': model,
+                'unique_id': model_key,
+                'materialization': node.get('config', {}).get('materialized'),
+                'schema': node.get('schema'),
+                'database': node.get('database'),
+                'upstream': upstream,
+                'downstream': downstream,
+                'description': node.get('description'),
+                'tags': node.get('tags', [])
+            }
+
+        except Exception as e:
+            logger.error(f"dbt_lineage failed: {e}")
+            return {'error': str(e)}

mcp-servers/data-platform/mcp_server/pandas_tools.py

@@ -0,0 +1,500 @@
+"""
+pandas MCP Tools.
+
+Provides DataFrame operations with Arrow IPC data_ref persistence.
+"""
+import pandas as pd
+import pyarrow as pa
+import pyarrow.parquet as pq
+import json
+import logging
+from pathlib import Path
+from typing import Dict, List, Optional, Any, Union
+
+from .data_store import DataStore
+from .config import load_config
+
+logger = logging.getLogger(__name__)
+
+
+class PandasTools:
+    """pandas data manipulation tools with data_ref persistence"""
+
+    def __init__(self):
+        self.store = DataStore.get_instance()
+        config = load_config()
+        self.max_rows = config.get('max_rows', 100_000)
+        self.store.set_max_rows(self.max_rows)
+
+    def _check_and_store(
+        self,
+        df: pd.DataFrame,
+        name: Optional[str] = None,
+        source: Optional[str] = None
+    ) -> Dict:
+        """Check row limit and store DataFrame if within limits"""
+        check = self.store.check_row_limit(len(df))
+        if check['exceeded']:
+            return {
+                'error': 'row_limit_exceeded',
+                **check,
+                'preview': df.head(100).to_dict(orient='records')
+            }
+
+        data_ref = self.store.store(df, name=name, source=source)
+        return {
+            'data_ref': data_ref,
+            'rows': len(df),
+            'columns': list(df.columns),
+            'dtypes': {col: str(dtype) for col, dtype in df.dtypes.items()}
+        }
+
+    async def read_csv(
+        self,
+        file_path: str,
+        name: Optional[str] = None,
+        chunk_size: Optional[int] = None,
+        **kwargs
+    ) -> Dict:
+        """
+        Load CSV file into DataFrame.
+
+        Args:
+            file_path: Path to CSV file
+            name: Optional name for data_ref
+            chunk_size: If provided, process in chunks
+            **kwargs: Additional pandas read_csv arguments
+
+        Returns:
+            Dict with data_ref or error info
+        """
+        path = Path(file_path)
+        if not path.exists():
+            return {'error': f'File not found: {file_path}'}
+
+        try:
+            if chunk_size:
+                # Chunked processing - return iterator info
+                chunks = []
+                for i, chunk in enumerate(pd.read_csv(path, chunksize=chunk_size, **kwargs)):
+                    chunk_ref = self.store.store(chunk, name=f"{name or 'chunk'}_{i}", source=file_path)
+                    chunks.append({'ref': chunk_ref, 'rows': len(chunk)})
+                return {
+                    'chunked': True,
+                    'chunks': chunks,
+                    'total_chunks': len(chunks)
+                }
+
+            df = pd.read_csv(path, **kwargs)
+            return self._check_and_store(df, name=name, source=file_path)
+
+        except Exception as e:
+            logger.error(f"read_csv failed: {e}")
+            return {'error': str(e)}
+
+    async def read_parquet(
+        self,
+        file_path: str,
+        name: Optional[str] = None,
+        columns: Optional[List[str]] = None
+    ) -> Dict:
+        """
+        Load Parquet file into DataFrame.
+
+        Args:
+            file_path: Path to Parquet file
+            name: Optional name for data_ref
+            columns: Optional list of columns to load
+
+        Returns:
+            Dict with data_ref or error info
+        """
+        path = Path(file_path)
+        if not path.exists():
+            return {'error': f'File not found: {file_path}'}
+
+        try:
+            table = pq.read_table(path, columns=columns)
+            df = table.to_pandas()
+            return self._check_and_store(df, name=name, source=file_path)
+
+        except Exception as e:
+            logger.error(f"read_parquet failed: {e}")
+            return {'error': str(e)}
+
+    async def read_json(
+        self,
+        file_path: str,
+        name: Optional[str] = None,
+        lines: bool = False,
+        **kwargs
+    ) -> Dict:
+        """
+        Load JSON/JSONL file into DataFrame.
+
+        Args:
+            file_path: Path to JSON file
+            name: Optional name for data_ref
+            lines: If True, read as JSON Lines format
+            **kwargs: Additional pandas read_json arguments
+
+        Returns:
+            Dict with data_ref or error info
+        """
+        path = Path(file_path)
+        if not path.exists():
+            return {'error': f'File not found: {file_path}'}
+
+        try:
+            df = pd.read_json(path, lines=lines, **kwargs)
+            return self._check_and_store(df, name=name, source=file_path)
+
+        except Exception as e:
+            logger.error(f"read_json failed: {e}")
+            return {'error': str(e)}
+
+    async def to_csv(
+        self,
+        data_ref: str,
+        file_path: str,
+        index: bool = False,
+        **kwargs
+    ) -> Dict:
+        """
+        Export DataFrame to CSV file.
+
+        Args:
+            data_ref: Reference to stored DataFrame
+            file_path: Output file path
+            index: Whether to include index
+            **kwargs: Additional pandas to_csv arguments
+
+        Returns:
+            Dict with success status
+        """
+        df = self.store.get_pandas(data_ref)
+        if df is None:
+            return {'error': f'DataFrame not found: {data_ref}'}
+
+        try:
+            df.to_csv(file_path, index=index, **kwargs)
+            return {
+                'success': True,
+                'file_path': file_path,
+                'rows': len(df),
+                'size_bytes': Path(file_path).stat().st_size
+            }
+        except Exception as e:
+            logger.error(f"to_csv failed: {e}")
+            return {'error': str(e)}
+
+    async def to_parquet(
+        self,
+        data_ref: str,
+        file_path: str,
+        compression: str = 'snappy'
+    ) -> Dict:
+        """
+        Export DataFrame to Parquet file.
+
+        Args:
+            data_ref: Reference to stored DataFrame
+            file_path: Output file path
+            compression: Compression codec
+
+        Returns:
+            Dict with success status
+        """
+        table = self.store.get(data_ref)
+        if table is None:
+            return {'error': f'DataFrame not found: {data_ref}'}
+
+        try:
+            pq.write_table(table, file_path, compression=compression)
+            return {
+                'success': True,
+                'file_path': file_path,
+                'rows': table.num_rows,
+                'size_bytes': Path(file_path).stat().st_size
+            }
+        except Exception as e:
+            logger.error(f"to_parquet failed: {e}")
+            return {'error': str(e)}
+
+    async def describe(self, data_ref: str) -> Dict:
+        """
+        Get statistical summary of DataFrame.
+
+        Args:
+            data_ref: Reference to stored DataFrame
+
+        Returns:
+            Dict with statistical summary
+        """
+        df = self.store.get_pandas(data_ref)
+        if df is None:
+            return {'error': f'DataFrame not found: {data_ref}'}
+
+        try:
+            desc = df.describe(include='all')
+            info = self.store.get_info(data_ref)
+
+            return {
+                'data_ref': data_ref,
+                'shape': {'rows': len(df), 'columns': len(df.columns)},
+                'columns': list(df.columns),
+                'dtypes': {col: str(dtype) for col, dtype in df.dtypes.items()},
+                'memory_mb': info.memory_bytes / (1024 * 1024) if info else None,
+                'null_counts': df.isnull().sum().to_dict(),
+                'statistics': desc.to_dict()
+            }
+        except Exception as e:
+            logger.error(f"describe failed: {e}")
+            return {'error': str(e)}
+
+    async def head(self, data_ref: str, n: int = 10) -> Dict:
+        """
+        Get first N rows of DataFrame.
+
+        Args:
+            data_ref: Reference to stored DataFrame
+            n: Number of rows
+
+        Returns:
+            Dict with rows as records
+        """
+        df = self.store.get_pandas(data_ref)
+        if df is None:
+            return {'error': f'DataFrame not found: {data_ref}'}
+
+        try:
+            head_df = df.head(n)
+            return {
+                'data_ref': data_ref,
+                'total_rows': len(df),
+                'returned_rows': len(head_df),
+                'columns': list(df.columns),
+                'data': head_df.to_dict(orient='records')
+            }
+        except Exception as e:
+            logger.error(f"head failed: {e}")
+            return {'error': str(e)}
+
+    async def tail(self, data_ref: str, n: int = 10) -> Dict:
+        """
+        Get last N rows of DataFrame.
+
+        Args:
+            data_ref: Reference to stored DataFrame
+            n: Number of rows
+
+        Returns:
+            Dict with rows as records
+        """
+        df = self.store.get_pandas(data_ref)
+        if df is None:
+            return {'error': f'DataFrame not found: {data_ref}'}
+
+        try:
+            tail_df = df.tail(n)
+            return {
+                'data_ref': data_ref,
+                'total_rows': len(df),
+                'returned_rows': len(tail_df),
+                'columns': list(df.columns),
+                'data': tail_df.to_dict(orient='records')
+            }
+        except Exception as e:
+            logger.error(f"tail failed: {e}")
+            return {'error': str(e)}
+
+    async def filter(
+        self,
+        data_ref: str,
+        condition: str,
+        name: Optional[str] = None
+    ) -> Dict:
+        """
+        Filter DataFrame rows by condition.
+
+        Args:
+            data_ref: Reference to stored DataFrame
+            condition: pandas query string (e.g., "age > 30 and city == 'NYC'")
+            name: Optional name for result data_ref
+
+        Returns:
+            Dict with new data_ref for filtered result
+        """
+        df = self.store.get_pandas(data_ref)
+        if df is None:
+            return {'error': f'DataFrame not found: {data_ref}'}
+
+        try:
+            filtered = df.query(condition)
+            result_name = name or f"{data_ref}_filtered"
+            return self._check_and_store(
+                filtered,
+                name=result_name,
+                source=f"filter({data_ref}, '{condition}')"
+            )
+        except Exception as e:
+            logger.error(f"filter failed: {e}")
+            return {'error': str(e)}
+
+    async def select(
+        self,
+        data_ref: str,
+        columns: List[str],
+        name: Optional[str] = None
+    ) -> Dict:
+        """
+        Select specific columns from DataFrame.
+
+        Args:
+            data_ref: Reference to stored DataFrame
+            columns: List of column names to select
+            name: Optional name for result data_ref
+
+        Returns:
+            Dict with new data_ref for selected columns
+        """
+        df = self.store.get_pandas(data_ref)
+        if df is None:
+            return {'error': f'DataFrame not found: {data_ref}'}
+
+        try:
+            # Validate columns exist
+            missing = [c for c in columns if c not in df.columns]
+            if missing:
+                return {
+                    'error': f'Columns not found: {missing}',
+                    'available_columns': list(df.columns)
+                }
+
+            selected = df[columns]
+            result_name = name or f"{data_ref}_select"
+            return self._check_and_store(
+                selected,
+                name=result_name,
+                source=f"select({data_ref}, {columns})"
+            )
+        except Exception as e:
+            logger.error(f"select failed: {e}")
+            return {'error': str(e)}
+
+    async def groupby(
+        self,
+        data_ref: str,
+        by: Union[str, List[str]],
+        agg: Dict[str, Union[str, List[str]]],
+        name: Optional[str] = None
+    ) -> Dict:
+        """
+        Group DataFrame and aggregate.
+
+        Args:
+            data_ref: Reference to stored DataFrame
+            by: Column(s) to group by
+            agg: Aggregation dict (e.g., {"sales": "sum", "count": "mean"})
+            name: Optional name for result data_ref
+
+        Returns:
+            Dict with new data_ref for aggregated result
+        """
+        df = self.store.get_pandas(data_ref)
+        if df is None:
+            return {'error': f'DataFrame not found: {data_ref}'}
+
+        try:
+            grouped = df.groupby(by).agg(agg).reset_index()
+            # Flatten column names if multi-level
+            if isinstance(grouped.columns, pd.MultiIndex):
+                grouped.columns = ['_'.join(col).strip('_') for col in grouped.columns]
+
+            result_name = name or f"{data_ref}_grouped"
+            return self._check_and_store(
+                grouped,
+                name=result_name,
+                source=f"groupby({data_ref}, by={by})"
+            )
+        except Exception as e:
+            logger.error(f"groupby failed: {e}")
+            return {'error': str(e)}
+
+    async def join(
+        self,
+        left_ref: str,
+        right_ref: str,
+        on: Optional[Union[str, List[str]]] = None,
+        left_on: Optional[Union[str, List[str]]] = None,
+        right_on: Optional[Union[str, List[str]]] = None,
+        how: str = 'inner',
+        name: Optional[str] = None
+    ) -> Dict:
+        """
+        Join two DataFrames.
+
+        Args:
+            left_ref: Reference to left DataFrame
+            right_ref: Reference to right DataFrame
+            on: Column(s) to join on (if same name in both)
+            left_on: Left join column(s)
+            right_on: Right join column(s)
+            how: Join type ('inner', 'left', 'right', 'outer')
+            name: Optional name for result data_ref
+
+        Returns:
+            Dict with new data_ref for joined result
+        """
+        left_df = self.store.get_pandas(left_ref)
+        right_df = self.store.get_pandas(right_ref)
+
+        if left_df is None:
+            return {'error': f'DataFrame not found: {left_ref}'}
+        if right_df is None:
+            return {'error': f'DataFrame not found: {right_ref}'}
+
+        try:
+            joined = pd.merge(
+                left_df, right_df,
+                on=on, left_on=left_on, right_on=right_on,
+                how=how
+            )
+            result_name = name or f"{left_ref}_{right_ref}_joined"
+            return self._check_and_store(
+                joined,
+                name=result_name,
+                source=f"join({left_ref}, {right_ref}, how={how})"
+            )
+        except Exception as e:
+            logger.error(f"join failed: {e}")
+            return {'error': str(e)}
+
+    async def list_data(self) -> Dict:
+        """
+        List all stored DataFrames.
+
+        Returns:
+            Dict with list of stored DataFrames and their info
+        """
+        refs = self.store.list_refs()
+        return {
+            'count': len(refs),
+            'total_memory_mb': self.store.total_memory_mb(),
+            'max_rows_limit': self.max_rows,
+            'dataframes': refs
+        }
+
+    async def drop_data(self, data_ref: str) -> Dict:
+        """
+        Remove a DataFrame from storage.
+
+        Args:
+            data_ref: Reference to drop
+
+        Returns:
+            Dict with success status
+        """
+        if self.store.drop(data_ref):
+            return {'success': True, 'dropped': data_ref}
+        return {'error': f'DataFrame not found: {data_ref}'}

mcp-servers/data-platform/mcp_server/postgres_tools.py

@@ -0,0 +1,538 @@
+"""
+PostgreSQL/PostGIS MCP Tools.
+
+Provides database operations with connection pooling and PostGIS support.
+"""
+import asyncio
+import logging
+from typing import Dict, List, Optional, Any
+import json
+
+from .data_store import DataStore
+from .config import load_config
+
+logger = logging.getLogger(__name__)
+
+# Optional imports - gracefully handle missing dependencies
+try:
+    import asyncpg
+    ASYNCPG_AVAILABLE = True
+except ImportError:
+    ASYNCPG_AVAILABLE = False
+    logger.warning("asyncpg not available - PostgreSQL tools will be disabled")
+
+try:
+    import pandas as pd
+    PANDAS_AVAILABLE = True
+except ImportError:
+    PANDAS_AVAILABLE = False
+
+
+class PostgresTools:
+    """PostgreSQL/PostGIS database tools"""
+
+    def __init__(self):
+        self.store = DataStore.get_instance()
+        self.config = load_config()
+        self.pool: Optional[Any] = None
+        self.max_rows = self.config.get('max_rows', 100_000)
+
+    async def _get_pool(self):
+        """Get or create connection pool"""
+        if not ASYNCPG_AVAILABLE:
+            raise RuntimeError("asyncpg not installed - run: pip install asyncpg")
+
+        if self.pool is None:
+            postgres_url = self.config.get('postgres_url')
+            if not postgres_url:
+                raise RuntimeError(
+                    "PostgreSQL not configured. Set POSTGRES_URL in "
+                    "~/.config/claude/postgres.env"
+                )
+            self.pool = await asyncpg.create_pool(postgres_url, min_size=1, max_size=5)
+        return self.pool
+
+    async def pg_connect(self) -> Dict:
+        """
+        Test PostgreSQL connection and return status.
+
+        Returns:
+            Dict with connection status, version, and database info
+        """
+        if not ASYNCPG_AVAILABLE:
+            return {
+                'connected': False,
+                'error': 'asyncpg not installed',
+                'suggestion': 'pip install asyncpg'
+            }
+
+        postgres_url = self.config.get('postgres_url')
+        if not postgres_url:
+            return {
+                'connected': False,
+                'error': 'POSTGRES_URL not configured',
+                'suggestion': 'Create ~/.config/claude/postgres.env with POSTGRES_URL=postgresql://...'
+            }
+
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                version = await conn.fetchval('SELECT version()')
+                db_name = await conn.fetchval('SELECT current_database()')
+                user = await conn.fetchval('SELECT current_user')
+
+                # Check for PostGIS
+                postgis_version = None
+                try:
+                    postgis_version = await conn.fetchval('SELECT PostGIS_Version()')
+                except Exception:
+                    pass
+
+                return {
+                    'connected': True,
+                    'database': db_name,
+                    'user': user,
+                    'version': version.split(',')[0] if version else 'Unknown',
+                    'postgis_version': postgis_version,
+                    'postgis_available': postgis_version is not None
+                }
+
+        except Exception as e:
+            logger.error(f"pg_connect failed: {e}")
+            return {
+                'connected': False,
+                'error': str(e)
+            }
+
+    async def pg_query(
+        self,
+        query: str,
+        params: Optional[List] = None,
+        name: Optional[str] = None
+    ) -> Dict:
+        """
+        Execute SELECT query and return results as data_ref.
+
+        Args:
+            query: SQL SELECT query
+            params: Query parameters (positional, use $1, $2, etc.)
+            name: Optional name for result data_ref
+
+        Returns:
+            Dict with data_ref for results or error
+        """
+        if not PANDAS_AVAILABLE:
+            return {'error': 'pandas not available'}
+
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                if params:
+                    rows = await conn.fetch(query, *params)
+                else:
+                    rows = await conn.fetch(query)
+
+                if not rows:
+                    return {
+                        'data_ref': None,
+                        'rows': 0,
+                        'message': 'Query returned no results'
+                    }
+
+                # Convert to DataFrame
+                df = pd.DataFrame([dict(r) for r in rows])
+
+                # Check row limit
+                check = self.store.check_row_limit(len(df))
+                if check['exceeded']:
+                    return {
+                        'error': 'row_limit_exceeded',
+                        **check,
+                        'preview': df.head(100).to_dict(orient='records')
+                    }
+
+                # Store result
+                data_ref = self.store.store(df, name=name, source=f"pg_query: {query[:100]}...")
+                return {
+                    'data_ref': data_ref,
+                    'rows': len(df),
+                    'columns': list(df.columns)
+                }
+
+        except Exception as e:
+            logger.error(f"pg_query failed: {e}")
+            return {'error': str(e)}
+
+    async def pg_execute(
+        self,
+        query: str,
+        params: Optional[List] = None
+    ) -> Dict:
+        """
+        Execute INSERT/UPDATE/DELETE query.
+
+        Args:
+            query: SQL DML query
+            params: Query parameters
+
+        Returns:
+            Dict with affected rows count
+        """
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                if params:
+                    result = await conn.execute(query, *params)
+                else:
+                    result = await conn.execute(query)
+
+                # Parse result (e.g., "INSERT 0 1" or "UPDATE 5")
+                parts = result.split()
+                affected = int(parts[-1]) if parts else 0
+
+                return {
+                    'success': True,
+                    'command': parts[0] if parts else 'UNKNOWN',
+                    'affected_rows': affected
+                }
+
+        except Exception as e:
+            logger.error(f"pg_execute failed: {e}")
+            return {'error': str(e)}
+
+    async def pg_tables(self, schema: str = 'public') -> Dict:
+        """
+        List all tables in schema.
+
+        Args:
+            schema: Schema name (default: public)
+
+        Returns:
+            Dict with list of tables
+        """
+        query = """
+            SELECT
+                table_name,
+                table_type,
+                (SELECT count(*) FROM information_schema.columns c
+                 WHERE c.table_schema = t.table_schema
+                 AND c.table_name = t.table_name) as column_count
+            FROM information_schema.tables t
+            WHERE table_schema = $1
+            ORDER BY table_name
+        """
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                rows = await conn.fetch(query, schema)
+                tables = [
+                    {
+                        'name': r['table_name'],
+                        'type': r['table_type'],
+                        'columns': r['column_count']
+                    }
+                    for r in rows
+                ]
+                return {
+                    'schema': schema,
+                    'count': len(tables),
+                    'tables': tables
+                }
+        except Exception as e:
+            logger.error(f"pg_tables failed: {e}")
+            return {'error': str(e)}
+
+    async def pg_columns(self, table: str, schema: str = 'public') -> Dict:
+        """
+        Get column information for a table.
+
+        Args:
+            table: Table name
+            schema: Schema name (default: public)
+
+        Returns:
+            Dict with column details
+        """
+        query = """
+            SELECT
+                column_name,
+                data_type,
+                udt_name,
+                is_nullable,
+                column_default,
+                character_maximum_length,
+                numeric_precision
+            FROM information_schema.columns
+            WHERE table_schema = $1 AND table_name = $2
+            ORDER BY ordinal_position
+        """
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                rows = await conn.fetch(query, schema, table)
+                columns = [
+                    {
+                        'name': r['column_name'],
+                        'type': r['data_type'],
+                        'udt': r['udt_name'],
+                        'nullable': r['is_nullable'] == 'YES',
+                        'default': r['column_default'],
+                        'max_length': r['character_maximum_length'],
+                        'precision': r['numeric_precision']
+                    }
+                    for r in rows
+                ]
+                return {
+                    'table': f'{schema}.{table}',
+                    'column_count': len(columns),
+                    'columns': columns
+                }
+        except Exception as e:
+            logger.error(f"pg_columns failed: {e}")
+            return {'error': str(e)}
+
+    async def pg_schemas(self) -> Dict:
+        """
+        List all schemas in database.
+
+        Returns:
+            Dict with list of schemas
+        """
+        query = """
+            SELECT schema_name
+            FROM information_schema.schemata
+            WHERE schema_name NOT IN ('pg_catalog', 'information_schema', 'pg_toast')
+            ORDER BY schema_name
+        """
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                rows = await conn.fetch(query)
+                schemas = [r['schema_name'] for r in rows]
+                return {
+                    'count': len(schemas),
+                    'schemas': schemas
+                }
+        except Exception as e:
+            logger.error(f"pg_schemas failed: {e}")
+            return {'error': str(e)}
+
+    async def st_tables(self, schema: str = 'public') -> Dict:
+        """
+        List PostGIS-enabled tables.
+
+        Args:
+            schema: Schema name (default: public)
+
+        Returns:
+            Dict with list of tables with geometry columns
+        """
+        query = """
+            SELECT
+                f_table_name as table_name,
+                f_geometry_column as geometry_column,
+                type as geometry_type,
+                srid,
+                coord_dimension
+            FROM geometry_columns
+            WHERE f_table_schema = $1
+            ORDER BY f_table_name
+        """
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                rows = await conn.fetch(query, schema)
+                tables = [
+                    {
+                        'table': r['table_name'],
+                        'geometry_column': r['geometry_column'],
+                        'geometry_type': r['geometry_type'],
+                        'srid': r['srid'],
+                        'dimensions': r['coord_dimension']
+                    }
+                    for r in rows
+                ]
+                return {
+                    'schema': schema,
+                    'count': len(tables),
+                    'postgis_tables': tables
+                }
+        except Exception as e:
+            if 'geometry_columns' in str(e):
+                return {
+                    'error': 'PostGIS not installed or extension not enabled',
+                    'suggestion': 'Run: CREATE EXTENSION IF NOT EXISTS postgis;'
+                }
+            logger.error(f"st_tables failed: {e}")
+            return {'error': str(e)}
+
+    async def st_geometry_type(self, table: str, column: str, schema: str = 'public') -> Dict:
+        """
+        Get geometry type of a column.
+
+        Args:
+            table: Table name
+            column: Geometry column name
+            schema: Schema name
+
+        Returns:
+            Dict with geometry type information
+        """
+        query = f"""
+            SELECT DISTINCT ST_GeometryType({column}) as geom_type
+            FROM {schema}.{table}
+            WHERE {column} IS NOT NULL
+            LIMIT 10
+        """
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                rows = await conn.fetch(query)
+                types = [r['geom_type'] for r in rows]
+                return {
+                    'table': f'{schema}.{table}',
+                    'column': column,
+                    'geometry_types': types
+                }
+        except Exception as e:
+            logger.error(f"st_geometry_type failed: {e}")
+            return {'error': str(e)}
+
+    async def st_srid(self, table: str, column: str, schema: str = 'public') -> Dict:
+        """
+        Get SRID of geometry column.
+
+        Args:
+            table: Table name
+            column: Geometry column name
+            schema: Schema name
+
+        Returns:
+            Dict with SRID information
+        """
+        query = f"""
+            SELECT DISTINCT ST_SRID({column}) as srid
+            FROM {schema}.{table}
+            WHERE {column} IS NOT NULL
+            LIMIT 1
+        """
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                row = await conn.fetchrow(query)
+                srid = row['srid'] if row else None
+
+                # Get SRID description
+                srid_info = None
+                if srid:
+                    srid_query = """
+                        SELECT srtext, proj4text
+                        FROM spatial_ref_sys
+                        WHERE srid = $1
+                    """
+                    srid_row = await conn.fetchrow(srid_query, srid)
+                    if srid_row:
+                        srid_info = {
+                            'description': srid_row['srtext'][:200] if srid_row['srtext'] else None,
+                            'proj4': srid_row['proj4text']
+                        }
+
+                return {
+                    'table': f'{schema}.{table}',
+                    'column': column,
+                    'srid': srid,
+                    'info': srid_info
+                }
+        except Exception as e:
+            logger.error(f"st_srid failed: {e}")
+            return {'error': str(e)}
+
+    async def st_extent(self, table: str, column: str, schema: str = 'public') -> Dict:
+        """
+        Get bounding box of all geometries.
+
+        Args:
+            table: Table name
+            column: Geometry column name
+            schema: Schema name
+
+        Returns:
+            Dict with bounding box coordinates
+        """
+        query = f"""
+            SELECT
+                ST_XMin(extent) as xmin,
+                ST_YMin(extent) as ymin,
+                ST_XMax(extent) as xmax,
+                ST_YMax(extent) as ymax
+            FROM (
+                SELECT ST_Extent({column}) as extent
+                FROM {schema}.{table}
+            ) sub
+        """
+        try:
+            pool = await self._get_pool()
+            async with pool.acquire() as conn:
+                row = await conn.fetchrow(query)
+                if row and row['xmin'] is not None:
+                    return {
+                        'table': f'{schema}.{table}',
+                        'column': column,
+                        'bbox': {
+                            'xmin': float(row['xmin']),
+                            'ymin': float(row['ymin']),
+                            'xmax': float(row['xmax']),
+                            'ymax': float(row['ymax'])
+                        }
+                    }
+                return {
+                    'table': f'{schema}.{table}',
+                    'column': column,
+                    'bbox': None,
+                    'message': 'No geometries found or all NULL'
+                }
+        except Exception as e:
+            logger.error(f"st_extent failed: {e}")
+            return {'error': str(e)}
+
+    async def close(self):
+        """Close connection pool"""
+        if self.pool:
+            await self.pool.close()
+            self.pool = None
+
+
+def check_connection() -> None:
+    """
+    Check PostgreSQL connection for SessionStart hook.
+    Prints warning to stderr if connection fails.
+    """
+    import sys
+
+    config = load_config()
+    if not config.get('postgres_url'):
+        print(
+            "[data-platform] PostgreSQL not configured (POSTGRES_URL not set)",
+            file=sys.stderr
+        )
+        return
+
+    async def test():
+        try:
+            if not ASYNCPG_AVAILABLE:
+                print(
+                    "[data-platform] asyncpg not installed - PostgreSQL tools unavailable",
+                    file=sys.stderr
+                )
+                return
+
+            conn = await asyncpg.connect(config['postgres_url'], timeout=5)
+            await conn.close()
+            print("[data-platform] PostgreSQL connection OK", file=sys.stderr)
+        except Exception as e:
+            print(
+                f"[data-platform] PostgreSQL connection failed: {e}",
+                file=sys.stderr
+            )
+
+    asyncio.run(test())

mcp-servers/data-platform/mcp_server/server.py

@@ -0,0 +1,795 @@
+"""
+MCP Server entry point for Data Platform integration.
+
+Provides pandas, PostgreSQL/PostGIS, and dbt tools to Claude Code via JSON-RPC 2.0 over stdio.
+"""
+import asyncio
+import logging
+import json
+from mcp.server import Server
+from mcp.server.stdio import stdio_server
+from mcp.types import Tool, TextContent
+
+from .config import DataPlatformConfig
+from .data_store import DataStore
+from .pandas_tools import PandasTools
+from .postgres_tools import PostgresTools
+from .dbt_tools import DbtTools
+
+# Suppress noisy MCP validation warnings on stderr
+logging.basicConfig(level=logging.INFO)
+logging.getLogger("root").setLevel(logging.ERROR)
+logging.getLogger("mcp").setLevel(logging.ERROR)
+logger = logging.getLogger(__name__)
+
+
+class DataPlatformMCPServer:
+    """MCP Server for data platform integration"""
+
+    def __init__(self):
+        self.server = Server("data-platform-mcp")
+        self.config = None
+        self.pandas_tools = None
+        self.postgres_tools = None
+        self.dbt_tools = None
+
+    async def initialize(self):
+        """Initialize server and load configuration."""
+        try:
+            config_loader = DataPlatformConfig()
+            self.config = config_loader.load()
+
+            self.pandas_tools = PandasTools()
+            self.postgres_tools = PostgresTools()
+            self.dbt_tools = DbtTools()
+
+            # Log available capabilities
+            caps = []
+            caps.append("pandas")
+            if self.config.get('postgres_available'):
+                caps.append("PostgreSQL")
+            if self.config.get('dbt_available'):
+                caps.append("dbt")
+
+            logger.info(f"Data Platform MCP Server initialized with: {', '.join(caps)}")
+
+        except Exception as e:
+            logger.error(f"Failed to initialize: {e}")
+            raise
+
+    def setup_tools(self):
+        """Register all available tools with the MCP server"""
+
+        @self.server.list_tools()
+        async def list_tools() -> list[Tool]:
+            """Return list of available tools"""
+            tools = [
+                # pandas tools - always available
+                Tool(
+                    name="read_csv",
+                    description="Load CSV file into DataFrame",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "file_path": {
+                                "type": "string",
+                                "description": "Path to CSV file"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Optional name for data_ref"
+                            },
+                            "chunk_size": {
+                                "type": "integer",
+                                "description": "Process in chunks of this size"
+                            }
+                        },
+                        "required": ["file_path"]
+                    }
+                ),
+                Tool(
+                    name="read_parquet",
+                    description="Load Parquet file into DataFrame",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "file_path": {
+                                "type": "string",
+                                "description": "Path to Parquet file"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Optional name for data_ref"
+                            },
+                            "columns": {
+                                "type": "array",
+                                "items": {"type": "string"},
+                                "description": "Optional list of columns to load"
+                            }
+                        },
+                        "required": ["file_path"]
+                    }
+                ),
+                Tool(
+                    name="read_json",
+                    description="Load JSON/JSONL file into DataFrame",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "file_path": {
+                                "type": "string",
+                                "description": "Path to JSON file"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Optional name for data_ref"
+                            },
+                            "lines": {
+                                "type": "boolean",
+                                "default": False,
+                                "description": "Read as JSON Lines format"
+                            }
+                        },
+                        "required": ["file_path"]
+                    }
+                ),
+                Tool(
+                    name="to_csv",
+                    description="Export DataFrame to CSV file",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to stored DataFrame"
+                            },
+                            "file_path": {
+                                "type": "string",
+                                "description": "Output file path"
+                            },
+                            "index": {
+                                "type": "boolean",
+                                "default": False,
+                                "description": "Include index column"
+                            }
+                        },
+                        "required": ["data_ref", "file_path"]
+                    }
+                ),
+                Tool(
+                    name="to_parquet",
+                    description="Export DataFrame to Parquet file",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to stored DataFrame"
+                            },
+                            "file_path": {
+                                "type": "string",
+                                "description": "Output file path"
+                            },
+                            "compression": {
+                                "type": "string",
+                                "default": "snappy",
+                                "description": "Compression codec"
+                            }
+                        },
+                        "required": ["data_ref", "file_path"]
+                    }
+                ),
+                Tool(
+                    name="describe",
+                    description="Get statistical summary of DataFrame",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to stored DataFrame"
+                            }
+                        },
+                        "required": ["data_ref"]
+                    }
+                ),
+                Tool(
+                    name="head",
+                    description="Get first N rows of DataFrame",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to stored DataFrame"
+                            },
+                            "n": {
+                                "type": "integer",
+                                "default": 10,
+                                "description": "Number of rows"
+                            }
+                        },
+                        "required": ["data_ref"]
+                    }
+                ),
+                Tool(
+                    name="tail",
+                    description="Get last N rows of DataFrame",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to stored DataFrame"
+                            },
+                            "n": {
+                                "type": "integer",
+                                "default": 10,
+                                "description": "Number of rows"
+                            }
+                        },
+                        "required": ["data_ref"]
+                    }
+                ),
+                Tool(
+                    name="filter",
+                    description="Filter DataFrame rows by condition",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to stored DataFrame"
+                            },
+                            "condition": {
+                                "type": "string",
+                                "description": "pandas query string (e.g., 'age > 30 and city == \"NYC\"')"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Optional name for result data_ref"
+                            }
+                        },
+                        "required": ["data_ref", "condition"]
+                    }
+                ),
+                Tool(
+                    name="select",
+                    description="Select specific columns from DataFrame",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to stored DataFrame"
+                            },
+                            "columns": {
+                                "type": "array",
+                                "items": {"type": "string"},
+                                "description": "List of column names to select"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Optional name for result data_ref"
+                            }
+                        },
+                        "required": ["data_ref", "columns"]
+                    }
+                ),
+                Tool(
+                    name="groupby",
+                    description="Group DataFrame and aggregate",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to stored DataFrame"
+                            },
+                            "by": {
+                                "oneOf": [
+                                    {"type": "string"},
+                                    {"type": "array", "items": {"type": "string"}}
+                                ],
+                                "description": "Column(s) to group by"
+                            },
+                            "agg": {
+                                "type": "object",
+                                "description": "Aggregation dict (e.g., {\"sales\": \"sum\", \"count\": \"mean\"})"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Optional name for result data_ref"
+                            }
+                        },
+                        "required": ["data_ref", "by", "agg"]
+                    }
+                ),
+                Tool(
+                    name="join",
+                    description="Join two DataFrames",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "left_ref": {
+                                "type": "string",
+                                "description": "Reference to left DataFrame"
+                            },
+                            "right_ref": {
+                                "type": "string",
+                                "description": "Reference to right DataFrame"
+                            },
+                            "on": {
+                                "oneOf": [
+                                    {"type": "string"},
+                                    {"type": "array", "items": {"type": "string"}}
+                                ],
+                                "description": "Column(s) to join on (if same name in both)"
+                            },
+                            "left_on": {
+                                "oneOf": [
+                                    {"type": "string"},
+                                    {"type": "array", "items": {"type": "string"}}
+                                ],
+                                "description": "Left join column(s)"
+                            },
+                            "right_on": {
+                                "oneOf": [
+                                    {"type": "string"},
+                                    {"type": "array", "items": {"type": "string"}}
+                                ],
+                                "description": "Right join column(s)"
+                            },
+                            "how": {
+                                "type": "string",
+                                "enum": ["inner", "left", "right", "outer"],
+                                "default": "inner",
+                                "description": "Join type"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Optional name for result data_ref"
+                            }
+                        },
+                        "required": ["left_ref", "right_ref"]
+                    }
+                ),
+                Tool(
+                    name="list_data",
+                    description="List all stored DataFrames",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {}
+                    }
+                ),
+                Tool(
+                    name="drop_data",
+                    description="Remove a DataFrame from storage",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "data_ref": {
+                                "type": "string",
+                                "description": "Reference to drop"
+                            }
+                        },
+                        "required": ["data_ref"]
+                    }
+                ),
+                # PostgreSQL tools
+                Tool(
+                    name="pg_connect",
+                    description="Test PostgreSQL connection and return status",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {}
+                    }
+                ),
+                Tool(
+                    name="pg_query",
+                    description="Execute SELECT query and return results as data_ref",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "query": {
+                                "type": "string",
+                                "description": "SQL SELECT query"
+                            },
+                            "params": {
+                                "type": "array",
+                                "items": {},
+                                "description": "Query parameters (use $1, $2, etc.)"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Optional name for result data_ref"
+                            }
+                        },
+                        "required": ["query"]
+                    }
+                ),
+                Tool(
+                    name="pg_execute",
+                    description="Execute INSERT/UPDATE/DELETE query",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "query": {
+                                "type": "string",
+                                "description": "SQL DML query"
+                            },
+                            "params": {
+                                "type": "array",
+                                "items": {},
+                                "description": "Query parameters"
+                            }
+                        },
+                        "required": ["query"]
+                    }
+                ),
+                Tool(
+                    name="pg_tables",
+                    description="List all tables in schema",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "schema": {
+                                "type": "string",
+                                "default": "public",
+                                "description": "Schema name"
+                            }
+                        }
+                    }
+                ),
+                Tool(
+                    name="pg_columns",
+                    description="Get column information for a table",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "table": {
+                                "type": "string",
+                                "description": "Table name"
+                            },
+                            "schema": {
+                                "type": "string",
+                                "default": "public",
+                                "description": "Schema name"
+                            }
+                        },
+                        "required": ["table"]
+                    }
+                ),
+                Tool(
+                    name="pg_schemas",
+                    description="List all schemas in database",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {}
+                    }
+                ),
+                # PostGIS tools
+                Tool(
+                    name="st_tables",
+                    description="List PostGIS-enabled tables",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "schema": {
+                                "type": "string",
+                                "default": "public",
+                                "description": "Schema name"
+                            }
+                        }
+                    }
+                ),
+                Tool(
+                    name="st_geometry_type",
+                    description="Get geometry type of a column",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "table": {
+                                "type": "string",
+                                "description": "Table name"
+                            },
+                            "column": {
+                                "type": "string",
+                                "description": "Geometry column name"
+                            },
+                            "schema": {
+                                "type": "string",
+                                "default": "public",
+                                "description": "Schema name"
+                            }
+                        },
+                        "required": ["table", "column"]
+                    }
+                ),
+                Tool(
+                    name="st_srid",
+                    description="Get SRID of geometry column",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "table": {
+                                "type": "string",
+                                "description": "Table name"
+                            },
+                            "column": {
+                                "type": "string",
+                                "description": "Geometry column name"
+                            },
+                            "schema": {
+                                "type": "string",
+                                "default": "public",
+                                "description": "Schema name"
+                            }
+                        },
+                        "required": ["table", "column"]
+                    }
+                ),
+                Tool(
+                    name="st_extent",
+                    description="Get bounding box of all geometries",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "table": {
+                                "type": "string",
+                                "description": "Table name"
+                            },
+                            "column": {
+                                "type": "string",
+                                "description": "Geometry column name"
+                            },
+                            "schema": {
+                                "type": "string",
+                                "default": "public",
+                                "description": "Schema name"
+                            }
+                        },
+                        "required": ["table", "column"]
+                    }
+                ),
+                # dbt tools
+                Tool(
+                    name="dbt_parse",
+                    description="Validate dbt project (pre-flight check)",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {}
+                    }
+                ),
+                Tool(
+                    name="dbt_run",
+                    description="Run dbt models with pre-validation",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "select": {
+                                "type": "string",
+                                "description": "Model selection (e.g., 'model_name', '+model_name', 'tag:daily')"
+                            },
+                            "exclude": {
+                                "type": "string",
+                                "description": "Models to exclude"
+                            },
+                            "full_refresh": {
+                                "type": "boolean",
+                                "default": False,
+                                "description": "Rebuild incremental models"
+                            }
+                        }
+                    }
+                ),
+                Tool(
+                    name="dbt_test",
+                    description="Run dbt tests",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "select": {
+                                "type": "string",
+                                "description": "Test selection"
+                            },
+                            "exclude": {
+                                "type": "string",
+                                "description": "Tests to exclude"
+                            }
+                        }
+                    }
+                ),
+                Tool(
+                    name="dbt_build",
+                    description="Run dbt build (run + test) with pre-validation",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "select": {
+                                "type": "string",
+                                "description": "Model/test selection"
+                            },
+                            "exclude": {
+                                "type": "string",
+                                "description": "Resources to exclude"
+                            },
+                            "full_refresh": {
+                                "type": "boolean",
+                                "default": False,
+                                "description": "Rebuild incremental models"
+                            }
+                        }
+                    }
+                ),
+                Tool(
+                    name="dbt_compile",
+                    description="Compile dbt models to SQL without executing",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "select": {
+                                "type": "string",
+                                "description": "Model selection"
+                            }
+                        }
+                    }
+                ),
+                Tool(
+                    name="dbt_ls",
+                    description="List dbt resources",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "select": {
+                                "type": "string",
+                                "description": "Resource selection"
+                            },
+                            "resource_type": {
+                                "type": "string",
+                                "enum": ["model", "test", "seed", "snapshot", "source"],
+                                "description": "Filter by type"
+                            },
+                            "output": {
+                                "type": "string",
+                                "enum": ["name", "path", "json"],
+                                "default": "name",
+                                "description": "Output format"
+                            }
+                        }
+                    }
+                ),
+                Tool(
+                    name="dbt_docs_generate",
+                    description="Generate dbt documentation",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {}
+                    }
+                ),
+                Tool(
+                    name="dbt_lineage",
+                    description="Get model dependencies and lineage",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "model": {
+                                "type": "string",
+                                "description": "Model name to analyze"
+                            }
+                        },
+                        "required": ["model"]
+                    }
+                )
+            ]
+            return tools
+
+        @self.server.call_tool()
+        async def call_tool(name: str, arguments: dict) -> list[TextContent]:
+            """Handle tool invocation."""
+            try:
+                # Route to appropriate tool handler
+                # pandas tools
+                if name == "read_csv":
+                    result = await self.pandas_tools.read_csv(**arguments)
+                elif name == "read_parquet":
+                    result = await self.pandas_tools.read_parquet(**arguments)
+                elif name == "read_json":
+                    result = await self.pandas_tools.read_json(**arguments)
+                elif name == "to_csv":
+                    result = await self.pandas_tools.to_csv(**arguments)
+                elif name == "to_parquet":
+                    result = await self.pandas_tools.to_parquet(**arguments)
+                elif name == "describe":
+                    result = await self.pandas_tools.describe(**arguments)
+                elif name == "head":
+                    result = await self.pandas_tools.head(**arguments)
+                elif name == "tail":
+                    result = await self.pandas_tools.tail(**arguments)
+                elif name == "filter":
+                    result = await self.pandas_tools.filter(**arguments)
+                elif name == "select":
+                    result = await self.pandas_tools.select(**arguments)
+                elif name == "groupby":
+                    result = await self.pandas_tools.groupby(**arguments)
+                elif name == "join":
+                    result = await self.pandas_tools.join(**arguments)
+                elif name == "list_data":
+                    result = await self.pandas_tools.list_data()
+                elif name == "drop_data":
+                    result = await self.pandas_tools.drop_data(**arguments)
+                # PostgreSQL tools
+                elif name == "pg_connect":
+                    result = await self.postgres_tools.pg_connect()
+                elif name == "pg_query":
+                    result = await self.postgres_tools.pg_query(**arguments)
+                elif name == "pg_execute":
+                    result = await self.postgres_tools.pg_execute(**arguments)
+                elif name == "pg_tables":
+                    result = await self.postgres_tools.pg_tables(**arguments)
+                elif name == "pg_columns":
+                    result = await self.postgres_tools.pg_columns(**arguments)
+                elif name == "pg_schemas":
+                    result = await self.postgres_tools.pg_schemas()
+                # PostGIS tools
+                elif name == "st_tables":
+                    result = await self.postgres_tools.st_tables(**arguments)
+                elif name == "st_geometry_type":
+                    result = await self.postgres_tools.st_geometry_type(**arguments)
+                elif name == "st_srid":
+                    result = await self.postgres_tools.st_srid(**arguments)
+                elif name == "st_extent":
+                    result = await self.postgres_tools.st_extent(**arguments)
+                # dbt tools
+                elif name == "dbt_parse":
+                    result = await self.dbt_tools.dbt_parse()
+                elif name == "dbt_run":
+                    result = await self.dbt_tools.dbt_run(**arguments)
+                elif name == "dbt_test":
+                    result = await self.dbt_tools.dbt_test(**arguments)
+                elif name == "dbt_build":
+                    result = await self.dbt_tools.dbt_build(**arguments)
+                elif name == "dbt_compile":
+                    result = await self.dbt_tools.dbt_compile(**arguments)
+                elif name == "dbt_ls":
+                    result = await self.dbt_tools.dbt_ls(**arguments)
+                elif name == "dbt_docs_generate":
+                    result = await self.dbt_tools.dbt_docs_generate()
+                elif name == "dbt_lineage":
+                    result = await self.dbt_tools.dbt_lineage(**arguments)
+                else:
+                    raise ValueError(f"Unknown tool: {name}")
+
+                return [TextContent(
+                    type="text",
+                    text=json.dumps(result, indent=2, default=str)
+                )]
+
+            except Exception as e:
+                logger.error(f"Tool {name} failed: {e}")
+                return [TextContent(
+                    type="text",
+                    text=json.dumps({"error": str(e)}, indent=2)
+                )]
+
+    async def run(self):
+        """Run the MCP server"""
+        await self.initialize()
+        self.setup_tools()
+
+        async with stdio_server() as (read_stream, write_stream):
+            await self.server.run(
+                read_stream,
+                write_stream,
+                self.server.create_initialization_options()
+            )
+
+
+async def main():
+    """Main entry point"""
+    server = DataPlatformMCPServer()
+    await server.run()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

mcp-servers/data-platform/pyproject.toml

@@ -0,0 +1,49 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "data-platform-mcp"
+version = "1.0.0"
+description = "MCP Server for data engineering with pandas, PostgreSQL/PostGIS, and dbt"
+readme = "README.md"
+license = {text = "MIT"}
+requires-python = ">=3.10"
+authors = [
+    {name = "Leo Miranda"}
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+dependencies = [
+    "mcp>=0.9.0",
+    "pandas>=2.0.0",
+    "pyarrow>=14.0.0",
+    "asyncpg>=0.29.0",
+    "geoalchemy2>=0.14.0",
+    "shapely>=2.0.0",
+    "dbt-core>=1.9.0",
+    "dbt-postgres>=1.9.0",
+    "python-dotenv>=1.0.0",
+    "pydantic>=2.5.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.4.3",
+    "pytest-asyncio>=0.23.0",
+]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["mcp_server*"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]

mcp-servers/data-platform/requirements.txt

@@ -0,0 +1,23 @@
+# MCP SDK
+mcp>=0.9.0
+
+# Data Processing
+pandas>=2.0.0
+pyarrow>=14.0.0
+
+# PostgreSQL/PostGIS
+asyncpg>=0.29.0
+geoalchemy2>=0.14.0
+shapely>=2.0.0
+
+# dbt
+dbt-core>=1.9.0
+dbt-postgres>=1.9.0
+
+# Utilities
+python-dotenv>=1.0.0
+pydantic>=2.5.0
+
+# Testing
+pytest>=7.4.3
+pytest-asyncio>=0.23.0

mcp-servers/data-platform/tests/__init__.py

@@ -0,0 +1,3 @@
+"""
+Tests for Data Platform MCP Server.
+"""

mcp-servers/data-platform/tests/test_config.py

@@ -0,0 +1,239 @@
+"""
+Unit tests for configuration loader.
+"""
+import pytest
+from pathlib import Path
+import os
+
+
+def test_load_system_config(tmp_path, monkeypatch):
+    """Test loading system-level PostgreSQL configuration"""
+    # Import here to avoid import errors before setup
+    from mcp_server.config import DataPlatformConfig
+
+    # Mock home directory
+    config_dir = tmp_path / '.config' / 'claude'
+    config_dir.mkdir(parents=True)
+
+    config_file = config_dir / 'postgres.env'
+    config_file.write_text(
+        "POSTGRES_URL=postgresql://user:pass@localhost:5432/testdb\n"
+    )
+
+    monkeypatch.setenv('HOME', str(tmp_path))
+    monkeypatch.chdir(tmp_path)
+
+    config = DataPlatformConfig()
+    result = config.load()
+
+    assert result['postgres_url'] == 'postgresql://user:pass@localhost:5432/testdb'
+    assert result['postgres_available'] is True
+
+
+def test_postgres_optional(tmp_path, monkeypatch):
+    """Test that PostgreSQL configuration is optional"""
+    from mcp_server.config import DataPlatformConfig
+
+    # No postgres.env file
+    monkeypatch.setenv('HOME', str(tmp_path))
+    monkeypatch.chdir(tmp_path)
+
+    # Clear any existing env vars
+    monkeypatch.delenv('POSTGRES_URL', raising=False)
+
+    config = DataPlatformConfig()
+    result = config.load()
+
+    assert result['postgres_url'] is None
+    assert result['postgres_available'] is False
+
+
+def test_project_config_override(tmp_path, monkeypatch):
+    """Test that project config overrides system config"""
+    from mcp_server.config import DataPlatformConfig
+
+    # Set up system config
+    system_config_dir = tmp_path / '.config' / 'claude'
+    system_config_dir.mkdir(parents=True)
+
+    system_config = system_config_dir / 'postgres.env'
+    system_config.write_text(
+        "POSTGRES_URL=postgresql://system:pass@localhost:5432/systemdb\n"
+    )
+
+    # Set up project config
+    project_dir = tmp_path / 'project'
+    project_dir.mkdir()
+
+    project_config = project_dir / '.env'
+    project_config.write_text(
+        "POSTGRES_URL=postgresql://project:pass@localhost:5432/projectdb\n"
+        "DBT_PROJECT_DIR=/path/to/dbt\n"
+    )
+
+    monkeypatch.setenv('HOME', str(tmp_path))
+    monkeypatch.chdir(project_dir)
+
+    config = DataPlatformConfig()
+    result = config.load()
+
+    # Project config should override
+    assert result['postgres_url'] == 'postgresql://project:pass@localhost:5432/projectdb'
+    assert result['dbt_project_dir'] == '/path/to/dbt'
+
+
+def test_max_rows_config(tmp_path, monkeypatch):
+    """Test max rows configuration"""
+    from mcp_server.config import DataPlatformConfig
+
+    project_dir = tmp_path / 'project'
+    project_dir.mkdir()
+
+    project_config = project_dir / '.env'
+    project_config.write_text("DATA_PLATFORM_MAX_ROWS=50000\n")
+
+    monkeypatch.setenv('HOME', str(tmp_path))
+    monkeypatch.chdir(project_dir)
+
+    config = DataPlatformConfig()
+    result = config.load()
+
+    assert result['max_rows'] == 50000
+
+
+def test_default_max_rows(tmp_path, monkeypatch):
+    """Test default max rows value"""
+    from mcp_server.config import DataPlatformConfig
+
+    monkeypatch.setenv('HOME', str(tmp_path))
+    monkeypatch.chdir(tmp_path)
+
+    # Clear any existing env vars
+    monkeypatch.delenv('DATA_PLATFORM_MAX_ROWS', raising=False)
+
+    config = DataPlatformConfig()
+    result = config.load()
+
+    assert result['max_rows'] == 100_000  # Default value
+
+
+def test_dbt_auto_detection(tmp_path, monkeypatch):
+    """Test automatic dbt project detection"""
+    from mcp_server.config import DataPlatformConfig
+
+    # Create project with dbt_project.yml
+    project_dir = tmp_path / 'project'
+    project_dir.mkdir()
+    (project_dir / 'dbt_project.yml').write_text("name: test_project\n")
+
+    monkeypatch.setenv('HOME', str(tmp_path))
+    monkeypatch.chdir(project_dir)
+    # Clear PWD and DBT_PROJECT_DIR to ensure auto-detection
+    monkeypatch.delenv('PWD', raising=False)
+    monkeypatch.delenv('DBT_PROJECT_DIR', raising=False)
+    monkeypatch.delenv('CLAUDE_PROJECT_DIR', raising=False)
+
+    config = DataPlatformConfig()
+    result = config.load()
+
+    assert result['dbt_project_dir'] == str(project_dir)
+    assert result['dbt_available'] is True
+
+
+def test_dbt_subdirectory_detection(tmp_path, monkeypatch):
+    """Test dbt project detection in subdirectory"""
+    from mcp_server.config import DataPlatformConfig
+
+    # Create project with dbt in subdirectory
+    project_dir = tmp_path / 'project'
+    project_dir.mkdir()
+    # Need a marker file for _find_project_directory to find the project
+    (project_dir / '.git').mkdir()
+    dbt_dir = project_dir / 'transform'
+    dbt_dir.mkdir()
+    (dbt_dir / 'dbt_project.yml').write_text("name: test_project\n")
+
+    monkeypatch.setenv('HOME', str(tmp_path))
+    monkeypatch.chdir(project_dir)
+    # Clear env vars to ensure auto-detection
+    monkeypatch.delenv('PWD', raising=False)
+    monkeypatch.delenv('DBT_PROJECT_DIR', raising=False)
+    monkeypatch.delenv('CLAUDE_PROJECT_DIR', raising=False)
+
+    config = DataPlatformConfig()
+    result = config.load()
+
+    assert result['dbt_project_dir'] == str(dbt_dir)
+    assert result['dbt_available'] is True
+
+
+def test_no_dbt_project(tmp_path, monkeypatch):
+    """Test when no dbt project exists"""
+    from mcp_server.config import DataPlatformConfig
+
+    project_dir = tmp_path / 'project'
+    project_dir.mkdir()
+
+    monkeypatch.setenv('HOME', str(tmp_path))
+    monkeypatch.chdir(project_dir)
+
+    # Clear any existing env vars
+    monkeypatch.delenv('DBT_PROJECT_DIR', raising=False)
+
+    config = DataPlatformConfig()
+    result = config.load()
+
+    assert result['dbt_project_dir'] is None
+    assert result['dbt_available'] is False
+
+
+def test_find_project_directory_from_env(tmp_path, monkeypatch):
+    """Test finding project directory from CLAUDE_PROJECT_DIR env var"""
+    from mcp_server.config import DataPlatformConfig
+
+    project_dir = tmp_path / 'my-project'
+    project_dir.mkdir()
+    (project_dir / '.git').mkdir()
+
+    monkeypatch.setenv('CLAUDE_PROJECT_DIR', str(project_dir))
+
+    config = DataPlatformConfig()
+    result = config._find_project_directory()
+
+    assert result == project_dir
+
+
+def test_find_project_directory_from_cwd(tmp_path, monkeypatch):
+    """Test finding project directory from cwd with .env file"""
+    from mcp_server.config import DataPlatformConfig
+
+    project_dir = tmp_path / 'project'
+    project_dir.mkdir()
+    (project_dir / '.env').write_text("TEST=value")
+
+    monkeypatch.chdir(project_dir)
+    monkeypatch.delenv('CLAUDE_PROJECT_DIR', raising=False)
+    monkeypatch.delenv('PWD', raising=False)
+
+    config = DataPlatformConfig()
+    result = config._find_project_directory()
+
+    assert result == project_dir
+
+
+def test_find_project_directory_none_when_no_markers(tmp_path, monkeypatch):
+    """Test returns None when no project markers found"""
+    from mcp_server.config import DataPlatformConfig
+
+    empty_dir = tmp_path / 'empty'
+    empty_dir.mkdir()
+
+    monkeypatch.chdir(empty_dir)
+    monkeypatch.delenv('CLAUDE_PROJECT_DIR', raising=False)
+    monkeypatch.delenv('PWD', raising=False)
+    monkeypatch.delenv('DBT_PROJECT_DIR', raising=False)
+
+    config = DataPlatformConfig()
+    result = config._find_project_directory()
+
+    assert result is None

mcp-servers/data-platform/tests/test_data_store.py

@@ -0,0 +1,240 @@
+"""
+Unit tests for Arrow IPC DataFrame registry.
+"""
+import pytest
+import pandas as pd
+import pyarrow as pa
+
+
+def test_store_pandas_dataframe():
+    """Test storing pandas DataFrame"""
+    from mcp_server.data_store import DataStore
+
+    # Create fresh instance for test
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    df = pd.DataFrame({'a': [1, 2, 3], 'b': ['x', 'y', 'z']})
+    data_ref = store.store(df, name='test_df')
+
+    assert data_ref == 'test_df'
+    assert 'test_df' in store._dataframes
+    assert store._metadata['test_df'].rows == 3
+    assert store._metadata['test_df'].columns == 2
+
+
+def test_store_arrow_table():
+    """Test storing Arrow Table directly"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    table = pa.table({'x': [1, 2, 3], 'y': [4, 5, 6]})
+    data_ref = store.store(table, name='arrow_test')
+
+    assert data_ref == 'arrow_test'
+    assert store._dataframes['arrow_test'].num_rows == 3
+
+
+def test_store_auto_name():
+    """Test auto-generated data_ref names"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    df = pd.DataFrame({'a': [1, 2]})
+    data_ref = store.store(df)
+
+    assert data_ref.startswith('df_')
+    assert len(data_ref) == 11  # df_ + 8 hex chars
+
+
+def test_get_dataframe():
+    """Test retrieving stored DataFrame"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    df = pd.DataFrame({'a': [1, 2, 3]})
+    store.store(df, name='get_test')
+
+    result = store.get('get_test')
+    assert result is not None
+    assert result.num_rows == 3
+
+
+def test_get_pandas():
+    """Test retrieving as pandas DataFrame"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    df = pd.DataFrame({'a': [1, 2, 3], 'b': ['x', 'y', 'z']})
+    store.store(df, name='pandas_test')
+
+    result = store.get_pandas('pandas_test')
+    assert isinstance(result, pd.DataFrame)
+    assert list(result.columns) == ['a', 'b']
+    assert len(result) == 3
+
+
+def test_get_nonexistent():
+    """Test getting nonexistent data_ref returns None"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    assert store.get('nonexistent') is None
+    assert store.get_pandas('nonexistent') is None
+
+
+def test_list_refs():
+    """Test listing all stored DataFrames"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    store.store(pd.DataFrame({'a': [1, 2]}), name='df1')
+    store.store(pd.DataFrame({'b': [3, 4, 5]}), name='df2')
+
+    refs = store.list_refs()
+
+    assert len(refs) == 2
+    ref_names = [r['ref'] for r in refs]
+    assert 'df1' in ref_names
+    assert 'df2' in ref_names
+
+
+def test_drop_dataframe():
+    """Test dropping a DataFrame"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    store.store(pd.DataFrame({'a': [1]}), name='drop_test')
+    assert store.get('drop_test') is not None
+
+    result = store.drop('drop_test')
+    assert result is True
+    assert store.get('drop_test') is None
+
+
+def test_drop_nonexistent():
+    """Test dropping nonexistent data_ref"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    result = store.drop('nonexistent')
+    assert result is False
+
+
+def test_clear():
+    """Test clearing all DataFrames"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    store.store(pd.DataFrame({'a': [1]}), name='df1')
+    store.store(pd.DataFrame({'b': [2]}), name='df2')
+
+    store.clear()
+
+    assert len(store.list_refs()) == 0
+
+
+def test_get_info():
+    """Test getting DataFrame metadata"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    df = pd.DataFrame({'a': [1, 2, 3], 'b': ['x', 'y', 'z']})
+    store.store(df, name='info_test', source='test source')
+
+    info = store.get_info('info_test')
+
+    assert info.ref == 'info_test'
+    assert info.rows == 3
+    assert info.columns == 2
+    assert info.column_names == ['a', 'b']
+    assert info.source == 'test source'
+    assert info.memory_bytes > 0
+
+
+def test_total_memory():
+    """Test total memory calculation"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    store.store(pd.DataFrame({'a': range(100)}), name='df1')
+    store.store(pd.DataFrame({'b': range(200)}), name='df2')
+
+    total = store.total_memory_bytes()
+    assert total > 0
+
+    total_mb = store.total_memory_mb()
+    assert total_mb >= 0
+
+
+def test_check_row_limit():
+    """Test row limit checking"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._max_rows = 100
+
+    # Under limit
+    result = store.check_row_limit(50)
+    assert result['exceeded'] is False
+
+    # Over limit
+    result = store.check_row_limit(150)
+    assert result['exceeded'] is True
+    assert 'suggestion' in result
+
+
+def test_metadata_dtypes():
+    """Test that dtypes are correctly recorded"""
+    from mcp_server.data_store import DataStore
+
+    store = DataStore()
+    store._dataframes = {}
+    store._metadata = {}
+
+    df = pd.DataFrame({
+        'int_col': [1, 2, 3],
+        'float_col': [1.1, 2.2, 3.3],
+        'str_col': ['a', 'b', 'c']
+    })
+    store.store(df, name='dtype_test')
+
+    info = store.get_info('dtype_test')
+
+    assert 'int_col' in info.dtypes
+    assert 'float_col' in info.dtypes
+    assert 'str_col' in info.dtypes

mcp-servers/data-platform/tests/test_dbt_tools.py

@@ -0,0 +1,318 @@
+"""
+Unit tests for dbt MCP tools.
+"""
+import pytest
+from unittest.mock import Mock, patch, MagicMock
+import subprocess
+import json
+import tempfile
+import os
+
+
+@pytest.fixture
+def mock_config(tmp_path):
+    """Mock configuration with dbt project"""
+    dbt_dir = tmp_path / 'dbt_project'
+    dbt_dir.mkdir()
+    (dbt_dir / 'dbt_project.yml').write_text('name: test_project\n')
+
+    return {
+        'dbt_project_dir': str(dbt_dir),
+        'dbt_profiles_dir': str(tmp_path / '.dbt')
+    }
+
+
+@pytest.fixture
+def dbt_tools(mock_config):
+    """Create DbtTools instance with mocked config"""
+    with patch('mcp_server.dbt_tools.load_config', return_value=mock_config):
+        from mcp_server.dbt_tools import DbtTools
+
+        tools = DbtTools()
+        tools.project_dir = mock_config['dbt_project_dir']
+        tools.profiles_dir = mock_config['dbt_profiles_dir']
+        return tools
+
+
+@pytest.mark.asyncio
+async def test_dbt_parse_success(dbt_tools):
+    """Test successful dbt parse"""
+    mock_result = MagicMock()
+    mock_result.returncode = 0
+    mock_result.stdout = 'Parsed successfully'
+    mock_result.stderr = ''
+
+    with patch('subprocess.run', return_value=mock_result):
+        result = await dbt_tools.dbt_parse()
+
+    assert result['valid'] is True
+
+
+@pytest.mark.asyncio
+async def test_dbt_parse_failure(dbt_tools):
+    """Test dbt parse with errors"""
+    mock_result = MagicMock()
+    mock_result.returncode = 1
+    mock_result.stdout = ''
+    mock_result.stderr = 'Compilation error: deprecated syntax'
+
+    with patch('subprocess.run', return_value=mock_result):
+        result = await dbt_tools.dbt_parse()
+
+    assert result['valid'] is False
+    assert 'deprecated' in str(result.get('details', '')).lower() or len(result.get('errors', [])) > 0
+
+
+@pytest.mark.asyncio
+async def test_dbt_run_with_prevalidation(dbt_tools):
+    """Test dbt run includes pre-validation"""
+    # First call is parse, second is run
+    mock_parse = MagicMock()
+    mock_parse.returncode = 0
+    mock_parse.stdout = 'OK'
+    mock_parse.stderr = ''
+
+    mock_run = MagicMock()
+    mock_run.returncode = 0
+    mock_run.stdout = 'Completed successfully'
+    mock_run.stderr = ''
+
+    with patch('subprocess.run', side_effect=[mock_parse, mock_run]):
+        result = await dbt_tools.dbt_run()
+
+    assert result['success'] is True
+
+
+@pytest.mark.asyncio
+async def test_dbt_run_fails_validation(dbt_tools):
+    """Test dbt run fails if validation fails"""
+    mock_parse = MagicMock()
+    mock_parse.returncode = 1
+    mock_parse.stdout = ''
+    mock_parse.stderr = 'Parse error'
+
+    with patch('subprocess.run', return_value=mock_parse):
+        result = await dbt_tools.dbt_run()
+
+    assert 'error' in result
+    assert 'Pre-validation failed' in result['error']
+
+
+@pytest.mark.asyncio
+async def test_dbt_run_with_selection(dbt_tools):
+    """Test dbt run with model selection"""
+    mock_parse = MagicMock()
+    mock_parse.returncode = 0
+    mock_parse.stdout = 'OK'
+    mock_parse.stderr = ''
+
+    mock_run = MagicMock()
+    mock_run.returncode = 0
+    mock_run.stdout = 'Completed'
+    mock_run.stderr = ''
+
+    calls = []
+
+    def track_calls(*args, **kwargs):
+        calls.append(args[0] if args else kwargs.get('args', []))
+        if len(calls) == 1:
+            return mock_parse
+        return mock_run
+
+    with patch('subprocess.run', side_effect=track_calls):
+        result = await dbt_tools.dbt_run(select='dim_customers')
+
+    # Verify --select was passed
+    assert any('--select' in str(call) for call in calls)
+
+
+@pytest.mark.asyncio
+async def test_dbt_test(dbt_tools):
+    """Test dbt test"""
+    mock_result = MagicMock()
+    mock_result.returncode = 0
+    mock_result.stdout = 'All tests passed'
+    mock_result.stderr = ''
+
+    with patch('subprocess.run', return_value=mock_result):
+        result = await dbt_tools.dbt_test()
+
+    assert result['success'] is True
+
+
+@pytest.mark.asyncio
+async def test_dbt_build(dbt_tools):
+    """Test dbt build with pre-validation"""
+    mock_parse = MagicMock()
+    mock_parse.returncode = 0
+    mock_parse.stdout = 'OK'
+    mock_parse.stderr = ''
+
+    mock_build = MagicMock()
+    mock_build.returncode = 0
+    mock_build.stdout = 'Build complete'
+    mock_build.stderr = ''
+
+    with patch('subprocess.run', side_effect=[mock_parse, mock_build]):
+        result = await dbt_tools.dbt_build()
+
+    assert result['success'] is True
+
+
+@pytest.mark.asyncio
+async def test_dbt_compile(dbt_tools):
+    """Test dbt compile"""
+    mock_result = MagicMock()
+    mock_result.returncode = 0
+    mock_result.stdout = 'Compiled'
+    mock_result.stderr = ''
+
+    with patch('subprocess.run', return_value=mock_result):
+        result = await dbt_tools.dbt_compile()
+
+    assert result['success'] is True
+
+
+@pytest.mark.asyncio
+async def test_dbt_ls(dbt_tools):
+    """Test dbt ls"""
+    mock_result = MagicMock()
+    mock_result.returncode = 0
+    mock_result.stdout = 'dim_customers\ndim_products\nfct_orders\n'
+    mock_result.stderr = ''
+
+    with patch('subprocess.run', return_value=mock_result):
+        result = await dbt_tools.dbt_ls()
+
+    assert result['success'] is True
+    assert result['count'] == 3
+    assert 'dim_customers' in result['resources']
+
+
+@pytest.mark.asyncio
+async def test_dbt_docs_generate(dbt_tools, tmp_path):
+    """Test dbt docs generate"""
+    mock_result = MagicMock()
+    mock_result.returncode = 0
+    mock_result.stdout = 'Done'
+    mock_result.stderr = ''
+
+    # Create fake target directory
+    target_dir = tmp_path / 'dbt_project' / 'target'
+    target_dir.mkdir(parents=True)
+    (target_dir / 'catalog.json').write_text('{}')
+    (target_dir / 'manifest.json').write_text('{}')
+
+    dbt_tools.project_dir = str(tmp_path / 'dbt_project')
+
+    with patch('subprocess.run', return_value=mock_result):
+        result = await dbt_tools.dbt_docs_generate()
+
+    assert result['success'] is True
+    assert result['catalog_generated'] is True
+    assert result['manifest_generated'] is True
+
+
+@pytest.mark.asyncio
+async def test_dbt_lineage(dbt_tools, tmp_path):
+    """Test dbt lineage"""
+    # Create manifest
+    target_dir = tmp_path / 'dbt_project' / 'target'
+    target_dir.mkdir(parents=True)
+
+    manifest = {
+        'nodes': {
+            'model.test.dim_customers': {
+                'name': 'dim_customers',
+                'resource_type': 'model',
+                'schema': 'public',
+                'database': 'testdb',
+                'description': 'Customer dimension',
+                'tags': ['daily'],
+                'config': {'materialized': 'table'},
+                'depends_on': {
+                    'nodes': ['model.test.stg_customers']
+                }
+            },
+            'model.test.stg_customers': {
+                'name': 'stg_customers',
+                'resource_type': 'model',
+                'depends_on': {'nodes': []}
+            },
+            'model.test.fct_orders': {
+                'name': 'fct_orders',
+                'resource_type': 'model',
+                'depends_on': {
+                    'nodes': ['model.test.dim_customers']
+                }
+            }
+        }
+    }
+    (target_dir / 'manifest.json').write_text(json.dumps(manifest))
+
+    dbt_tools.project_dir = str(tmp_path / 'dbt_project')
+
+    result = await dbt_tools.dbt_lineage('dim_customers')
+
+    assert result['model'] == 'dim_customers'
+    assert 'model.test.stg_customers' in result['upstream']
+    assert 'model.test.fct_orders' in result['downstream']
+
+
+@pytest.mark.asyncio
+async def test_dbt_lineage_model_not_found(dbt_tools, tmp_path):
+    """Test dbt lineage with nonexistent model"""
+    target_dir = tmp_path / 'dbt_project' / 'target'
+    target_dir.mkdir(parents=True)
+
+    manifest = {
+        'nodes': {
+            'model.test.dim_customers': {
+                'name': 'dim_customers',
+                'resource_type': 'model'
+            }
+        }
+    }
+    (target_dir / 'manifest.json').write_text(json.dumps(manifest))
+
+    dbt_tools.project_dir = str(tmp_path / 'dbt_project')
+
+    result = await dbt_tools.dbt_lineage('nonexistent_model')
+
+    assert 'error' in result
+    assert 'not found' in result['error'].lower()
+
+
+@pytest.mark.asyncio
+async def test_dbt_no_project():
+    """Test dbt tools when no project configured"""
+    with patch('mcp_server.dbt_tools.load_config', return_value={'dbt_project_dir': None}):
+        from mcp_server.dbt_tools import DbtTools
+
+        tools = DbtTools()
+        tools.project_dir = None
+
+        result = await tools.dbt_run()
+
+    assert 'error' in result
+    assert 'not found' in result['error'].lower()
+
+
+@pytest.mark.asyncio
+async def test_dbt_timeout(dbt_tools):
+    """Test dbt command timeout handling"""
+    with patch('subprocess.run', side_effect=subprocess.TimeoutExpired('dbt', 300)):
+        result = await dbt_tools.dbt_parse()
+
+    assert 'error' in result
+    assert 'timed out' in result['error'].lower()
+
+
+@pytest.mark.asyncio
+async def test_dbt_not_installed(dbt_tools):
+    """Test handling when dbt is not installed"""
+    with patch('subprocess.run', side_effect=FileNotFoundError()):
+        result = await dbt_tools.dbt_parse()
+
+    assert 'error' in result
+    assert 'not found' in result['error'].lower()

mcp-servers/data-platform/tests/test_pandas_tools.py

@@ -0,0 +1,301 @@
+"""
+Unit tests for pandas MCP tools.
+"""
+import pytest
+import pandas as pd
+import tempfile
+import os
+from pathlib import Path
+
+
+@pytest.fixture
+def temp_csv(tmp_path):
+    """Create a temporary CSV file for testing"""
+    csv_path = tmp_path / 'test.csv'
+    df = pd.DataFrame({
+        'id': [1, 2, 3, 4, 5],
+        'name': ['Alice', 'Bob', 'Charlie', 'Diana', 'Eve'],
+        'value': [10.5, 20.0, 30.5, 40.0, 50.5]
+    })
+    df.to_csv(csv_path, index=False)
+    return str(csv_path)
+
+
+@pytest.fixture
+def temp_parquet(tmp_path):
+    """Create a temporary Parquet file for testing"""
+    parquet_path = tmp_path / 'test.parquet'
+    df = pd.DataFrame({
+        'id': [1, 2, 3],
+        'data': ['a', 'b', 'c']
+    })
+    df.to_parquet(parquet_path)
+    return str(parquet_path)
+
+
+@pytest.fixture
+def temp_json(tmp_path):
+    """Create a temporary JSON file for testing"""
+    json_path = tmp_path / 'test.json'
+    df = pd.DataFrame({
+        'x': [1, 2],
+        'y': [3, 4]
+    })
+    df.to_json(json_path, orient='records')
+    return str(json_path)
+
+
+@pytest.fixture
+def pandas_tools():
+    """Create PandasTools instance with fresh store"""
+    from mcp_server.pandas_tools import PandasTools
+    from mcp_server.data_store import DataStore
+
+    # Reset store for test isolation
+    store = DataStore.get_instance()
+    store._dataframes = {}
+    store._metadata = {}
+
+    return PandasTools()
+
+
+@pytest.mark.asyncio
+async def test_read_csv(pandas_tools, temp_csv):
+    """Test reading CSV file"""
+    result = await pandas_tools.read_csv(temp_csv, name='csv_test')
+
+    assert 'data_ref' in result
+    assert result['data_ref'] == 'csv_test'
+    assert result['rows'] == 5
+    assert 'id' in result['columns']
+    assert 'name' in result['columns']
+
+
+@pytest.mark.asyncio
+async def test_read_csv_nonexistent(pandas_tools):
+    """Test reading nonexistent CSV file"""
+    result = await pandas_tools.read_csv('/nonexistent/path.csv')
+
+    assert 'error' in result
+    assert 'not found' in result['error'].lower()
+
+
+@pytest.mark.asyncio
+async def test_read_parquet(pandas_tools, temp_parquet):
+    """Test reading Parquet file"""
+    result = await pandas_tools.read_parquet(temp_parquet, name='parquet_test')
+
+    assert 'data_ref' in result
+    assert result['rows'] == 3
+
+
+@pytest.mark.asyncio
+async def test_read_json(pandas_tools, temp_json):
+    """Test reading JSON file"""
+    result = await pandas_tools.read_json(temp_json, name='json_test')
+
+    assert 'data_ref' in result
+    assert result['rows'] == 2
+
+
+@pytest.mark.asyncio
+async def test_to_csv(pandas_tools, temp_csv, tmp_path):
+    """Test exporting to CSV"""
+    # First load some data
+    await pandas_tools.read_csv(temp_csv, name='export_test')
+
+    # Export to new file
+    output_path = str(tmp_path / 'output.csv')
+    result = await pandas_tools.to_csv('export_test', output_path)
+
+    assert result['success'] is True
+    assert os.path.exists(output_path)
+
+
+@pytest.mark.asyncio
+async def test_to_parquet(pandas_tools, temp_csv, tmp_path):
+    """Test exporting to Parquet"""
+    await pandas_tools.read_csv(temp_csv, name='parquet_export')
+
+    output_path = str(tmp_path / 'output.parquet')
+    result = await pandas_tools.to_parquet('parquet_export', output_path)
+
+    assert result['success'] is True
+    assert os.path.exists(output_path)
+
+
+@pytest.mark.asyncio
+async def test_describe(pandas_tools, temp_csv):
+    """Test describe statistics"""
+    await pandas_tools.read_csv(temp_csv, name='describe_test')
+
+    result = await pandas_tools.describe('describe_test')
+
+    assert 'data_ref' in result
+    assert 'shape' in result
+    assert result['shape']['rows'] == 5
+    assert 'statistics' in result
+    assert 'null_counts' in result
+
+
+@pytest.mark.asyncio
+async def test_head(pandas_tools, temp_csv):
+    """Test getting first N rows"""
+    await pandas_tools.read_csv(temp_csv, name='head_test')
+
+    result = await pandas_tools.head('head_test', n=3)
+
+    assert result['returned_rows'] == 3
+    assert len(result['data']) == 3
+
+
+@pytest.mark.asyncio
+async def test_tail(pandas_tools, temp_csv):
+    """Test getting last N rows"""
+    await pandas_tools.read_csv(temp_csv, name='tail_test')
+
+    result = await pandas_tools.tail('tail_test', n=2)
+
+    assert result['returned_rows'] == 2
+
+
+@pytest.mark.asyncio
+async def test_filter(pandas_tools, temp_csv):
+    """Test filtering rows"""
+    await pandas_tools.read_csv(temp_csv, name='filter_test')
+
+    result = await pandas_tools.filter('filter_test', 'value > 25')
+
+    assert 'data_ref' in result
+    assert result['rows'] == 3  # 30.5, 40.0, 50.5
+
+
+@pytest.mark.asyncio
+async def test_filter_invalid_condition(pandas_tools, temp_csv):
+    """Test filter with invalid condition"""
+    await pandas_tools.read_csv(temp_csv, name='filter_error')
+
+    result = await pandas_tools.filter('filter_error', 'invalid_column > 0')
+
+    assert 'error' in result
+
+
+@pytest.mark.asyncio
+async def test_select(pandas_tools, temp_csv):
+    """Test selecting columns"""
+    await pandas_tools.read_csv(temp_csv, name='select_test')
+
+    result = await pandas_tools.select('select_test', ['id', 'name'])
+
+    assert 'data_ref' in result
+    assert result['columns'] == ['id', 'name']
+
+
+@pytest.mark.asyncio
+async def test_select_invalid_column(pandas_tools, temp_csv):
+    """Test select with invalid column"""
+    await pandas_tools.read_csv(temp_csv, name='select_error')
+
+    result = await pandas_tools.select('select_error', ['id', 'nonexistent'])
+
+    assert 'error' in result
+    assert 'available_columns' in result
+
+
+@pytest.mark.asyncio
+async def test_groupby(pandas_tools, tmp_path):
+    """Test groupby aggregation"""
+    # Create test data with groups
+    csv_path = tmp_path / 'groupby.csv'
+    df = pd.DataFrame({
+        'category': ['A', 'A', 'B', 'B'],
+        'value': [10, 20, 30, 40]
+    })
+    df.to_csv(csv_path, index=False)
+
+    await pandas_tools.read_csv(str(csv_path), name='groupby_test')
+
+    result = await pandas_tools.groupby(
+        'groupby_test',
+        by='category',
+        agg={'value': 'sum'}
+    )
+
+    assert 'data_ref' in result
+    assert result['rows'] == 2  # Two groups: A, B
+
+
+@pytest.mark.asyncio
+async def test_join(pandas_tools, tmp_path):
+    """Test joining DataFrames"""
+    # Create left table
+    left_path = tmp_path / 'left.csv'
+    pd.DataFrame({
+        'id': [1, 2, 3],
+        'name': ['A', 'B', 'C']
+    }).to_csv(left_path, index=False)
+
+    # Create right table
+    right_path = tmp_path / 'right.csv'
+    pd.DataFrame({
+        'id': [1, 2, 4],
+        'value': [100, 200, 400]
+    }).to_csv(right_path, index=False)
+
+    await pandas_tools.read_csv(str(left_path), name='left')
+    await pandas_tools.read_csv(str(right_path), name='right')
+
+    result = await pandas_tools.join('left', 'right', on='id', how='inner')
+
+    assert 'data_ref' in result
+    assert result['rows'] == 2  # Only id 1 and 2 match
+
+
+@pytest.mark.asyncio
+async def test_list_data(pandas_tools, temp_csv):
+    """Test listing all DataFrames"""
+    await pandas_tools.read_csv(temp_csv, name='list_test1')
+    await pandas_tools.read_csv(temp_csv, name='list_test2')
+
+    result = await pandas_tools.list_data()
+
+    assert result['count'] == 2
+    refs = [df['ref'] for df in result['dataframes']]
+    assert 'list_test1' in refs
+    assert 'list_test2' in refs
+
+
+@pytest.mark.asyncio
+async def test_drop_data(pandas_tools, temp_csv):
+    """Test dropping DataFrame"""
+    await pandas_tools.read_csv(temp_csv, name='drop_test')
+
+    result = await pandas_tools.drop_data('drop_test')
+
+    assert result['success'] is True
+
+    # Verify it's gone
+    list_result = await pandas_tools.list_data()
+    refs = [df['ref'] for df in list_result['dataframes']]
+    assert 'drop_test' not in refs
+
+
+@pytest.mark.asyncio
+async def test_drop_nonexistent(pandas_tools):
+    """Test dropping nonexistent DataFrame"""
+    result = await pandas_tools.drop_data('nonexistent')
+
+    assert 'error' in result
+
+
+@pytest.mark.asyncio
+async def test_operations_on_nonexistent(pandas_tools):
+    """Test operations on nonexistent data_ref"""
+    result = await pandas_tools.describe('nonexistent')
+    assert 'error' in result
+
+    result = await pandas_tools.head('nonexistent')
+    assert 'error' in result
+
+    result = await pandas_tools.filter('nonexistent', 'x > 0')
+    assert 'error' in result

mcp-servers/data-platform/tests/test_postgres_tools.py

@@ -0,0 +1,338 @@
+"""
+Unit tests for PostgreSQL MCP tools.
+"""
+import pytest
+from unittest.mock import Mock, AsyncMock, patch, MagicMock
+import pandas as pd
+
+
+@pytest.fixture
+def mock_config():
+    """Mock configuration"""
+    return {
+        'postgres_url': 'postgresql://test:test@localhost:5432/testdb',
+        'max_rows': 100000
+    }
+
+
+@pytest.fixture
+def postgres_tools(mock_config):
+    """Create PostgresTools instance with mocked config"""
+    with patch('mcp_server.postgres_tools.load_config', return_value=mock_config):
+        from mcp_server.postgres_tools import PostgresTools
+        from mcp_server.data_store import DataStore
+
+        # Reset store
+        store = DataStore.get_instance()
+        store._dataframes = {}
+        store._metadata = {}
+
+        tools = PostgresTools()
+        tools.config = mock_config
+        return tools
+
+
+@pytest.mark.asyncio
+async def test_pg_connect_no_config():
+    """Test pg_connect when no PostgreSQL configured"""
+    with patch('mcp_server.postgres_tools.load_config', return_value={'postgres_url': None}):
+        from mcp_server.postgres_tools import PostgresTools
+
+        tools = PostgresTools()
+        tools.config = {'postgres_url': None}
+
+        result = await tools.pg_connect()
+
+        assert result['connected'] is False
+        assert 'not configured' in result['error'].lower()
+
+
+@pytest.mark.asyncio
+async def test_pg_connect_success(postgres_tools):
+    """Test successful pg_connect"""
+    mock_conn = AsyncMock()
+    mock_conn.fetchval = AsyncMock(side_effect=[
+        'PostgreSQL 15.1',  # version
+        'testdb',           # database name
+        'testuser',         # user
+        None                # PostGIS check fails
+    ])
+    mock_conn.close = AsyncMock()
+
+    # Create proper async context manager
+    mock_cm = AsyncMock()
+    mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
+    mock_cm.__aexit__ = AsyncMock(return_value=None)
+
+    mock_pool = MagicMock()
+    mock_pool.acquire = MagicMock(return_value=mock_cm)
+
+    # Use AsyncMock for create_pool since it's awaited
+    with patch('asyncpg.create_pool', new=AsyncMock(return_value=mock_pool)):
+        postgres_tools.pool = None
+        result = await postgres_tools.pg_connect()
+
+    assert result['connected'] is True
+    assert result['database'] == 'testdb'
+
+
+@pytest.mark.asyncio
+async def test_pg_query_success(postgres_tools):
+    """Test successful pg_query"""
+    mock_rows = [
+        {'id': 1, 'name': 'Alice'},
+        {'id': 2, 'name': 'Bob'}
+    ]
+
+    mock_conn = AsyncMock()
+    mock_conn.fetch = AsyncMock(return_value=mock_rows)
+
+    mock_pool = AsyncMock()
+    mock_pool.acquire = MagicMock(return_value=AsyncMock(
+        __aenter__=AsyncMock(return_value=mock_conn),
+        __aexit__=AsyncMock()
+    ))
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.pg_query('SELECT * FROM users', name='users_data')
+
+    assert 'data_ref' in result
+    assert result['rows'] == 2
+
+
+@pytest.mark.asyncio
+async def test_pg_query_empty_result(postgres_tools):
+    """Test pg_query with no results"""
+    mock_conn = AsyncMock()
+    mock_conn.fetch = AsyncMock(return_value=[])
+
+    mock_pool = AsyncMock()
+    mock_pool.acquire = MagicMock(return_value=AsyncMock(
+        __aenter__=AsyncMock(return_value=mock_conn),
+        __aexit__=AsyncMock()
+    ))
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.pg_query('SELECT * FROM empty_table')
+
+    assert result['data_ref'] is None
+    assert result['rows'] == 0
+
+
+@pytest.mark.asyncio
+async def test_pg_execute_success(postgres_tools):
+    """Test successful pg_execute"""
+    mock_conn = AsyncMock()
+    mock_conn.execute = AsyncMock(return_value='INSERT 0 3')
+
+    mock_pool = AsyncMock()
+    mock_pool.acquire = MagicMock(return_value=AsyncMock(
+        __aenter__=AsyncMock(return_value=mock_conn),
+        __aexit__=AsyncMock()
+    ))
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.pg_execute('INSERT INTO users VALUES (1, 2, 3)')
+
+    assert result['success'] is True
+    assert result['affected_rows'] == 3
+    assert result['command'] == 'INSERT'
+
+
+@pytest.mark.asyncio
+async def test_pg_tables(postgres_tools):
+    """Test listing tables"""
+    mock_rows = [
+        {'table_name': 'users', 'table_type': 'BASE TABLE', 'column_count': 5},
+        {'table_name': 'orders', 'table_type': 'BASE TABLE', 'column_count': 8}
+    ]
+
+    mock_conn = AsyncMock()
+    mock_conn.fetch = AsyncMock(return_value=mock_rows)
+
+    mock_pool = AsyncMock()
+    mock_pool.acquire = MagicMock(return_value=AsyncMock(
+        __aenter__=AsyncMock(return_value=mock_conn),
+        __aexit__=AsyncMock()
+    ))
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.pg_tables(schema='public')
+
+    assert result['schema'] == 'public'
+    assert result['count'] == 2
+    assert len(result['tables']) == 2
+
+
+@pytest.mark.asyncio
+async def test_pg_columns(postgres_tools):
+    """Test getting column info"""
+    mock_rows = [
+        {
+            'column_name': 'id',
+            'data_type': 'integer',
+            'udt_name': 'int4',
+            'is_nullable': 'NO',
+            'column_default': "nextval('users_id_seq'::regclass)",
+            'character_maximum_length': None,
+            'numeric_precision': 32
+        },
+        {
+            'column_name': 'name',
+            'data_type': 'character varying',
+            'udt_name': 'varchar',
+            'is_nullable': 'YES',
+            'column_default': None,
+            'character_maximum_length': 255,
+            'numeric_precision': None
+        }
+    ]
+
+    mock_conn = AsyncMock()
+    mock_conn.fetch = AsyncMock(return_value=mock_rows)
+
+    mock_pool = AsyncMock()
+    mock_pool.acquire = MagicMock(return_value=AsyncMock(
+        __aenter__=AsyncMock(return_value=mock_conn),
+        __aexit__=AsyncMock()
+    ))
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.pg_columns(table='users')
+
+    assert result['table'] == 'public.users'
+    assert result['column_count'] == 2
+    assert result['columns'][0]['name'] == 'id'
+    assert result['columns'][0]['nullable'] is False
+
+
+@pytest.mark.asyncio
+async def test_pg_schemas(postgres_tools):
+    """Test listing schemas"""
+    mock_rows = [
+        {'schema_name': 'public'},
+        {'schema_name': 'app'}
+    ]
+
+    mock_conn = AsyncMock()
+    mock_conn.fetch = AsyncMock(return_value=mock_rows)
+
+    mock_pool = AsyncMock()
+    mock_pool.acquire = MagicMock(return_value=AsyncMock(
+        __aenter__=AsyncMock(return_value=mock_conn),
+        __aexit__=AsyncMock()
+    ))
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.pg_schemas()
+
+    assert result['count'] == 2
+    assert 'public' in result['schemas']
+
+
+@pytest.mark.asyncio
+async def test_st_tables(postgres_tools):
+    """Test listing PostGIS tables"""
+    mock_rows = [
+        {
+            'table_name': 'locations',
+            'geometry_column': 'geom',
+            'geometry_type': 'POINT',
+            'srid': 4326,
+            'coord_dimension': 2
+        }
+    ]
+
+    mock_conn = AsyncMock()
+    mock_conn.fetch = AsyncMock(return_value=mock_rows)
+
+    mock_pool = AsyncMock()
+    mock_pool.acquire = MagicMock(return_value=AsyncMock(
+        __aenter__=AsyncMock(return_value=mock_conn),
+        __aexit__=AsyncMock()
+    ))
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.st_tables()
+
+    assert result['count'] == 1
+    assert result['postgis_tables'][0]['table'] == 'locations'
+    assert result['postgis_tables'][0]['srid'] == 4326
+
+
+@pytest.mark.asyncio
+async def test_st_tables_no_postgis(postgres_tools):
+    """Test st_tables when PostGIS not installed"""
+    mock_conn = AsyncMock()
+    mock_conn.fetch = AsyncMock(side_effect=Exception("relation \"geometry_columns\" does not exist"))
+
+    # Create proper async context manager
+    mock_cm = AsyncMock()
+    mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
+    mock_cm.__aexit__ = AsyncMock(return_value=None)
+
+    mock_pool = MagicMock()
+    mock_pool.acquire = MagicMock(return_value=mock_cm)
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.st_tables()
+
+    assert 'error' in result
+    assert 'PostGIS' in result['error']
+
+
+@pytest.mark.asyncio
+async def test_st_extent(postgres_tools):
+    """Test getting geometry bounding box"""
+    mock_row = {
+        'xmin': -122.5,
+        'ymin': 37.5,
+        'xmax': -122.0,
+        'ymax': 38.0
+    }
+
+    mock_conn = AsyncMock()
+    mock_conn.fetchrow = AsyncMock(return_value=mock_row)
+
+    mock_pool = AsyncMock()
+    mock_pool.acquire = MagicMock(return_value=AsyncMock(
+        __aenter__=AsyncMock(return_value=mock_conn),
+        __aexit__=AsyncMock()
+    ))
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.st_extent(table='locations', column='geom')
+
+    assert result['bbox']['xmin'] == -122.5
+    assert result['bbox']['ymax'] == 38.0
+
+
+@pytest.mark.asyncio
+async def test_error_handling(postgres_tools):
+    """Test error handling for database errors"""
+    mock_conn = AsyncMock()
+    mock_conn.fetch = AsyncMock(side_effect=Exception("Connection refused"))
+
+    # Create proper async context manager
+    mock_cm = AsyncMock()
+    mock_cm.__aenter__ = AsyncMock(return_value=mock_conn)
+    mock_cm.__aexit__ = AsyncMock(return_value=None)
+
+    mock_pool = MagicMock()
+    mock_pool.acquire = MagicMock(return_value=mock_cm)
+
+    postgres_tools.pool = mock_pool
+
+    result = await postgres_tools.pg_query('SELECT 1')
+
+    assert 'error' in result
+    assert 'Connection refused' in result['error']

mcp-servers/gitea/mcp_server/gitea_client.py

@@ -621,6 +621,40 @@ class GiteaClient:
         response.raise_for_status()
         return response.json()
 
+    def create_org_label(
+        self,
+        org: str,
+        name: str,
+        color: str,
+        description: Optional[str] = None
+    ) -> Dict:
+        """
+        Create a new label at the organization level.
+
+        Organization labels are shared across all repositories in the org.
+        Use this for workflow labels (Type, Priority, Complexity, Effort, etc.)
+
+        Args:
+            org: Organization name
+            name: Label name (e.g., 'Type/Bug', 'Priority/High')
+            color: Hex color code (with or without #)
+            description: Optional label description
+
+        Returns:
+            Created label dictionary
+        """
+        url = f"{self.base_url}/orgs/{org}/labels"
+        data = {
+            'name': name,
+            'color': color.lstrip('#')  # Remove # if present
+        }
+        if description:
+            data['description'] = description
+        logger.info(f"Creating organization label '{name}' in {org}")
+        response = self.session.post(url, json=data)
+        response.raise_for_status()
+        return response.json()
+
     # ========================================
     # PULL REQUEST OPERATIONS
     # ========================================

mcp-servers/gitea/mcp_server/server.py

@@ -622,13 +622,65 @@ class GiteaMCPServer:
                 ),
                 Tool(
                     name="create_label",
-                    description="Create a new label in the repository",
+                    description="Create a new label in the repository (for repo-specific labels like Component/*, Tech/*)",
                     inputSchema={
                         "type": "object",
                         "properties": {
                             "name": {
                                 "type": "string",
-                                "description": "Label name"
+                                "description": "Label name (e.g., 'Component/Backend', 'Tech/Python')"
+                            },
+                            "color": {
+                                "type": "string",
+                                "description": "Label color (hex code)"
+                            },
+                            "description": {
+                                "type": "string",
+                                "description": "Label description"
+                            },
+                            "repo": {
+                                "type": "string",
+                                "description": "Repository name (owner/repo format)"
+                            }
+                        },
+                        "required": ["name", "color"]
+                    }
+                ),
+                Tool(
+                    name="create_org_label",
+                    description="Create a new label at organization level (for workflow labels like Type/*, Priority/*, Complexity/*, Effort/*)",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "org": {
+                                "type": "string",
+                                "description": "Organization name"
+                            },
+                            "name": {
+                                "type": "string",
+                                "description": "Label name (e.g., 'Type/Bug', 'Priority/High')"
+                            },
+                            "color": {
+                                "type": "string",
+                                "description": "Label color (hex code)"
+                            },
+                            "description": {
+                                "type": "string",
+                                "description": "Label description"
+                            }
+                        },
+                        "required": ["org", "name", "color"]
+                    }
+                ),
+                Tool(
+                    name="create_label_smart",
+                    description="Create a label at the appropriate level (org or repo) based on category. Org: Type/*, Priority/*, Complexity/*, Effort/*, Risk/*, Source/*, Agent/*. Repo: Component/*, Tech/*",
+                    inputSchema={
+                        "type": "object",
+                        "properties": {
+                            "name": {
+                                "type": "string",
+                                "description": "Label name (e.g., 'Type/Bug', 'Component/Backend')"
                             },
                             "color": {
                                 "type": "string",
@@ -880,6 +932,20 @@ class GiteaMCPServer:
                         arguments.get('description'),
                         arguments.get('repo')
                     )
+                elif name == "create_org_label":
+                    result = self.client.create_org_label(
+                        arguments['org'],
+                        arguments['name'],
+                        arguments['color'],
+                        arguments.get('description')
+                    )
+                elif name == "create_label_smart":
+                    result = await self.label_tools.create_label_smart(
+                        arguments['name'],
+                        arguments['color'],
+                        arguments.get('description'),
+                        arguments.get('repo')
+                    )
                 # Pull Request tools
                 elif name == "list_pull_requests":
                     result = await self.pr_tools.list_pull_requests(**arguments)

mcp-servers/gitea/mcp_server/tools/labels.py

@@ -259,3 +259,119 @@ class LabelTools:
             return lookup[category_lower][value_lower]
 
         return None
+
+    # Organization-level label categories (workflow labels shared across repos)
+    ORG_LABEL_CATEGORIES = {'agent', 'complexity', 'effort', 'efforts', 'priority', 'risk', 'source', 'type'}
+
+    # Repository-level label categories (project-specific labels)
+    REPO_LABEL_CATEGORIES = {'component', 'tech'}
+
+    async def create_label_smart(
+        self,
+        name: str,
+        color: str,
+        description: Optional[str] = None,
+        repo: Optional[str] = None
+    ) -> Dict:
+        """
+        Create a label at the appropriate level (org or repo) based on category.
+        Skips if label already exists (checks both org and repo levels).
+
+        Organization labels: Agent, Complexity, Effort, Priority, Risk, Source, Type
+        Repository labels: Component, Tech
+
+        Args:
+            name: Label name (e.g., 'Type/Bug', 'Component/Backend')
+            color: Hex color code
+            description: Optional label description
+            repo: Repository in 'owner/repo' format
+
+        Returns:
+            Created label dictionary with 'level' key, or 'skipped' if already exists
+        """
+        loop = asyncio.get_event_loop()
+
+        target_repo = repo or self.gitea.repo
+        if not target_repo or '/' not in target_repo:
+            raise ValueError("Use 'owner/repo' format (e.g. 'org/repo-name')")
+
+        owner = target_repo.split('/')[0]
+        is_org = await loop.run_in_executor(
+            None,
+            lambda: self.gitea.is_org_repo(target_repo)
+        )
+
+        # Fetch existing labels to check for duplicates
+        existing_labels = await self.get_labels(target_repo)
+        all_existing = existing_labels.get('organization', []) + existing_labels.get('repository', [])
+        existing_names = [label['name'].lower() for label in all_existing]
+
+        # Normalize the new label name for comparison
+        name_normalized = name.lower()
+
+        # Also check for format variations (Type/Bug vs Type: Bug)
+        name_variations = [name_normalized]
+        if '/' in name:
+            name_variations.append(name.replace('/', ': ').lower())
+            name_variations.append(name.replace('/', ':').lower())
+        elif ': ' in name:
+            name_variations.append(name.replace(': ', '/').lower())
+        elif ':' in name:
+            name_variations.append(name.replace(':', '/').lower())
+
+        # Check if label already exists in any format
+        for variation in name_variations:
+            if variation in existing_names:
+                logger.info(f"Label '{name}' already exists (found as '{variation}'), skipping")
+                return {
+                    'name': name,
+                    'skipped': True,
+                    'reason': f"Label already exists",
+                    'level': 'existing'
+                }
+
+        # Parse category from label name
+        category = None
+        if '/' in name:
+            category = name.split('/')[0].lower().rstrip('s')
+        elif ':' in name:
+            category = name.split(':')[0].strip().lower().rstrip('s')
+
+        # If it's an org repo and the category is an org-level category, create at org level
+        if is_org and category in self.ORG_LABEL_CATEGORIES:
+            result = await loop.run_in_executor(
+                None,
+                lambda: self.gitea.create_org_label(owner, name, color, description)
+            )
+            # Handle unexpected response types (API may return list or non-dict)
+            if not isinstance(result, dict):
+                logger.error(f"Unexpected API response type for org label: {type(result)} - {result}")
+                return {
+                    'name': name,
+                    'error': True,
+                    'reason': f"API returned {type(result).__name__} instead of dict: {result}",
+                    'level': 'organization'
+                }
+            result['level'] = 'organization'
+            result['skipped'] = False
+            logger.info(f"Created organization label '{name}' in {owner}")
+        else:
+            # Create at repo level
+            result = await loop.run_in_executor(
+                None,
+                lambda: self.gitea.create_label(name, color, description, target_repo)
+            )
+            # Handle unexpected response types (API may return list or non-dict)
+            if not isinstance(result, dict):
+                logger.error(f"Unexpected API response type for repo label: {type(result)} - {result}")
+                return {
+                    'name': name,
+                    'error': True,
+                    'reason': f"API returned {type(result).__name__} instead of dict: {result}",
+                    'level': 'repository'
+                }
+            result['level'] = 'repository'
+            result['skipped'] = False
+            logger.info(f"Created repository label '{name}' in {target_repo}")
+
+        return result

mcp-servers/netbox/mcp_server/netbox_client.py

@@ -4,6 +4,7 @@ NetBox API client for interacting with NetBox REST API.
 Provides a generic HTTP client with methods for all standard REST operations.
 Individual tool modules use this client for their specific endpoints.
 """
+import json
 import requests
 import logging
 from typing import List, Dict, Optional, Any, Union
@@ -83,7 +84,20 @@ class NetBoxClient:
         if response.status_code == 204 or not response.content:
             return None
 
-        return response.json()
+        # Parse JSON with diagnostic error handling
+        try:
+            return response.json()
+        except json.JSONDecodeError as e:
+            logger.error(
+                f"JSON decode failed. Status: {response.status_code}, "
+                f"Content-Length: {len(response.content)}, "
+                f"Content preview: {response.content[:200]!r}"
+            )
+            raise ValueError(
+                f"Invalid JSON response from NetBox: {e}. "
+                f"Status code: {response.status_code}, "
+                f"Content length: {len(response.content)} bytes"
+            ) from e
 
     def list(
         self,

mcp-servers/netbox/mcp_server/server.py

@@ -103,7 +103,19 @@ TOOL_DEFINITIONS = {
         'properties': {
             'id': {'type': 'integer', 'description': 'Site ID'},
             'name': {'type': 'string', 'description': 'New name'},
-            'status': {'type': 'string', 'description': 'New status'}
+            'slug': {'type': 'string', 'description': 'New slug'},
+            'status': {'type': 'string', 'description': 'Status'},
+            'region': {'type': 'integer', 'description': 'Region ID'},
+            'group': {'type': 'integer', 'description': 'Site group ID'},
+            'tenant': {'type': 'integer', 'description': 'Tenant ID'},
+            'facility': {'type': 'string', 'description': 'Facility name'},
+            'time_zone': {'type': 'string', 'description': 'Time zone'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'physical_address': {'type': 'string', 'description': 'Physical address'},
+            'shipping_address': {'type': 'string', 'description': 'Shipping address'},
+            'latitude': {'type': 'number', 'description': 'Latitude'},
+            'longitude': {'type': 'number', 'description': 'Longitude'},
+            'comments': {'type': 'string', 'description': 'Comments'}
         },
         'required': ['id']
     },
@@ -136,7 +148,14 @@ TOOL_DEFINITIONS = {
     },
     'dcim_update_location': {
         'description': 'Update an existing location',
-        'properties': {'id': {'type': 'integer', 'description': 'Location ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Location ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'slug': {'type': 'string', 'description': 'New slug'},
+            'site': {'type': 'integer', 'description': 'Site ID'},
+            'parent': {'type': 'integer', 'description': 'Parent location ID'},
+            'description': {'type': 'string', 'description': 'Description'}
+        },
         'required': ['id']
     },
     'dcim_delete_location': {
@@ -171,7 +190,18 @@ TOOL_DEFINITIONS = {
     },
     'dcim_update_rack': {
         'description': 'Update an existing rack',
-        'properties': {'id': {'type': 'integer', 'description': 'Rack ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Rack ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'site': {'type': 'integer', 'description': 'Site ID'},
+            'location': {'type': 'integer', 'description': 'Location ID'},
+            'status': {'type': 'string', 'description': 'Status'},
+            'role': {'type': 'integer', 'description': 'Role ID'},
+            'tenant': {'type': 'integer', 'description': 'Tenant ID'},
+            'u_height': {'type': 'integer', 'description': 'Rack height in U'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
+        },
         'required': ['id']
     },
     'dcim_delete_rack': {
@@ -198,7 +228,12 @@ TOOL_DEFINITIONS = {
     },
     'dcim_update_manufacturer': {
         'description': 'Update an existing manufacturer',
-        'properties': {'id': {'type': 'integer', 'description': 'Manufacturer ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Manufacturer ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'slug': {'type': 'string', 'description': 'New slug'},
+            'description': {'type': 'string', 'description': 'Description'}
+        },
         'required': ['id']
     },
     'dcim_delete_manufacturer': {
@@ -230,7 +265,16 @@ TOOL_DEFINITIONS = {
     },
     'dcim_update_device_type': {
         'description': 'Update an existing device type',
-        'properties': {'id': {'type': 'integer', 'description': 'Device type ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Device type ID'},
+            'manufacturer': {'type': 'integer', 'description': 'Manufacturer ID'},
+            'model': {'type': 'string', 'description': 'Model name'},
+            'slug': {'type': 'string', 'description': 'New slug'},
+            'u_height': {'type': 'number', 'description': 'Height in rack units'},
+            'is_full_depth': {'type': 'boolean', 'description': 'Is full depth'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
+        },
         'required': ['id']
     },
     'dcim_delete_device_type': {
@@ -259,7 +303,14 @@ TOOL_DEFINITIONS = {
     },
     'dcim_update_device_role': {
         'description': 'Update an existing device role',
-        'properties': {'id': {'type': 'integer', 'description': 'Device role ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Device role ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'slug': {'type': 'string', 'description': 'New slug'},
+            'color': {'type': 'string', 'description': 'Hex color code'},
+            'vm_role': {'type': 'boolean', 'description': 'Can be assigned to VMs'},
+            'description': {'type': 'string', 'description': 'Description'}
+        },
         'required': ['id']
     },
     'dcim_delete_device_role': {
@@ -290,7 +341,13 @@ TOOL_DEFINITIONS = {
     },
     'dcim_update_platform': {
         'description': 'Update an existing platform',
-        'properties': {'id': {'type': 'integer', 'description': 'Platform ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Platform ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'slug': {'type': 'string', 'description': 'New slug'},
+            'manufacturer': {'type': 'integer', 'description': 'Manufacturer ID'},
+            'description': {'type': 'string', 'description': 'Description'}
+        },
         'required': ['id']
     },
     'dcim_delete_platform': {
@@ -326,7 +383,13 @@ TOOL_DEFINITIONS = {
             'status': {'type': 'string', 'description': 'Device status'},
             'rack': {'type': 'integer', 'description': 'Rack ID'},
             'position': {'type': 'number', 'description': 'Position in rack'},
-            'serial': {'type': 'string', 'description': 'Serial number'}
+            'serial': {'type': 'string', 'description': 'Serial number'},
+            'platform': {'type': 'integer', 'description': 'Platform ID'},
+            'primary_ip4': {'type': 'integer', 'description': 'Primary IPv4 address ID'},
+            'primary_ip6': {'type': 'integer', 'description': 'Primary IPv6 address ID'},
+            'asset_tag': {'type': 'string', 'description': 'Asset tag'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
         },
         'required': ['name', 'device_type', 'role', 'site']
     },
@@ -335,7 +398,17 @@ TOOL_DEFINITIONS = {
         'properties': {
             'id': {'type': 'integer', 'description': 'Device ID'},
             'name': {'type': 'string', 'description': 'New name'},
-            'status': {'type': 'string', 'description': 'New status'}
+            'status': {'type': 'string', 'description': 'New status'},
+            'platform': {'type': 'integer', 'description': 'Platform ID'},
+            'primary_ip4': {'type': 'integer', 'description': 'Primary IPv4 address ID'},
+            'primary_ip6': {'type': 'integer', 'description': 'Primary IPv6 address ID'},
+            'serial': {'type': 'string', 'description': 'Serial number'},
+            'asset_tag': {'type': 'string', 'description': 'Asset tag'},
+            'site': {'type': 'integer', 'description': 'Site ID'},
+            'rack': {'type': 'integer', 'description': 'Rack ID'},
+            'position': {'type': 'number', 'description': 'Position in rack'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
         },
         'required': ['id']
     },
@@ -370,7 +443,18 @@ TOOL_DEFINITIONS = {
     },
     'dcim_update_interface': {
         'description': 'Update an existing interface',
-        'properties': {'id': {'type': 'integer', 'description': 'Interface ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Interface ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'type': {'type': 'string', 'description': 'Interface type'},
+            'enabled': {'type': 'boolean', 'description': 'Interface enabled'},
+            'mtu': {'type': 'integer', 'description': 'MTU'},
+            'mac_address': {'type': 'string', 'description': 'MAC address'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'mode': {'type': 'string', 'description': 'VLAN mode'},
+            'untagged_vlan': {'type': 'integer', 'description': 'Untagged VLAN ID'},
+            'tagged_vlans': {'type': 'array', 'description': 'Tagged VLAN IDs'}
+        },
         'required': ['id']
     },
     'dcim_delete_interface': {
@@ -404,7 +488,15 @@ TOOL_DEFINITIONS = {
     },
     'dcim_update_cable': {
         'description': 'Update an existing cable',
-        'properties': {'id': {'type': 'integer', 'description': 'Cable ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Cable ID'},
+            'type': {'type': 'string', 'description': 'Cable type'},
+            'status': {'type': 'string', 'description': 'Cable status'},
+            'label': {'type': 'string', 'description': 'Cable label'},
+            'color': {'type': 'string', 'description': 'Cable color'},
+            'length': {'type': 'number', 'description': 'Cable length'},
+            'length_unit': {'type': 'string', 'description': 'Length unit'}
+        },
         'required': ['id']
     },
     'dcim_delete_cable': {
@@ -492,7 +584,15 @@ TOOL_DEFINITIONS = {
     },
     'ipam_update_vrf': {
         'description': 'Update an existing VRF',
-        'properties': {'id': {'type': 'integer', 'description': 'VRF ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'VRF ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'rd': {'type': 'string', 'description': 'Route distinguisher'},
+            'tenant': {'type': 'integer', 'description': 'Tenant ID'},
+            'enforce_unique': {'type': 'boolean', 'description': 'Enforce unique IPs'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
+        },
         'required': ['id']
     },
     'ipam_delete_vrf': {
@@ -531,7 +631,19 @@ TOOL_DEFINITIONS = {
     },
     'ipam_update_prefix': {
         'description': 'Update an existing prefix',
-        'properties': {'id': {'type': 'integer', 'description': 'Prefix ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Prefix ID'},
+            'prefix': {'type': 'string', 'description': 'Prefix in CIDR notation'},
+            'status': {'type': 'string', 'description': 'Status'},
+            'site': {'type': 'integer', 'description': 'Site ID'},
+            'vrf': {'type': 'integer', 'description': 'VRF ID'},
+            'vlan': {'type': 'integer', 'description': 'VLAN ID'},
+            'role': {'type': 'integer', 'description': 'Role ID'},
+            'tenant': {'type': 'integer', 'description': 'Tenant ID'},
+            'is_pool': {'type': 'boolean', 'description': 'Is a pool'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
+        },
         'required': ['id']
     },
     'ipam_delete_prefix': {
@@ -582,7 +694,18 @@ TOOL_DEFINITIONS = {
     },
     'ipam_update_ip_address': {
         'description': 'Update an existing IP address',
-        'properties': {'id': {'type': 'integer', 'description': 'IP address ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'IP address ID'},
+            'address': {'type': 'string', 'description': 'IP address with prefix length'},
+            'status': {'type': 'string', 'description': 'Status'},
+            'vrf': {'type': 'integer', 'description': 'VRF ID'},
+            'tenant': {'type': 'integer', 'description': 'Tenant ID'},
+            'dns_name': {'type': 'string', 'description': 'DNS name'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'},
+            'assigned_object_type': {'type': 'string', 'description': 'Object type to assign to'},
+            'assigned_object_id': {'type': 'integer', 'description': 'Object ID to assign to'}
+        },
         'required': ['id']
     },
     'ipam_delete_ip_address': {
@@ -647,7 +770,18 @@ TOOL_DEFINITIONS = {
     },
     'ipam_update_vlan': {
         'description': 'Update an existing VLAN',
-        'properties': {'id': {'type': 'integer', 'description': 'VLAN ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'VLAN ID'},
+            'vid': {'type': 'integer', 'description': 'VLAN ID number'},
+            'name': {'type': 'string', 'description': 'VLAN name'},
+            'status': {'type': 'string', 'description': 'Status'},
+            'site': {'type': 'integer', 'description': 'Site ID'},
+            'group': {'type': 'integer', 'description': 'VLAN group ID'},
+            'tenant': {'type': 'integer', 'description': 'Tenant ID'},
+            'role': {'type': 'integer', 'description': 'Role ID'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
+        },
         'required': ['id']
     },
     'ipam_delete_vlan': {
@@ -757,16 +891,17 @@ TOOL_DEFINITIONS = {
         'properties': {'id': {'type': 'integer', 'description': 'Provider ID'}},
         'required': ['id']
     },
-    'circuits_list_circuit_types': {
+    # NOTE: circuit_types tools shortened to meet 28-char limit
+    'circ_list_types': {
         'description': 'List all circuit types in NetBox',
         'properties': {'name': {'type': 'string', 'description': 'Filter by name'}}
     },
-    'circuits_get_circuit_type': {
+    'circ_get_type': {
         'description': 'Get a specific circuit type by ID',
         'properties': {'id': {'type': 'integer', 'description': 'Circuit type ID'}},
         'required': ['id']
     },
-    'circuits_create_circuit_type': {
+    'circ_create_type': {
         'description': 'Create a new circuit type',
         'properties': {
             'name': {'type': 'string', 'description': 'Type name'},
@@ -809,19 +944,20 @@ TOOL_DEFINITIONS = {
         'properties': {'id': {'type': 'integer', 'description': 'Circuit ID'}},
         'required': ['id']
     },
-    'circuits_list_circuit_terminations': {
+    # NOTE: circuit_terminations tools shortened to meet 28-char limit
+    'circ_list_terminations': {
         'description': 'List all circuit terminations in NetBox',
         'properties': {
             'circuit_id': {'type': 'integer', 'description': 'Filter by circuit ID'},
             'site_id': {'type': 'integer', 'description': 'Filter by site ID'}
         }
     },
-    'circuits_get_circuit_termination': {
+    'circ_get_termination': {
         'description': 'Get a specific circuit termination by ID',
         'properties': {'id': {'type': 'integer', 'description': 'Termination ID'}},
         'required': ['id']
     },
-    'circuits_create_circuit_termination': {
+    'circ_create_termination': {
         'description': 'Create a new circuit termination',
         'properties': {
             'circuit': {'type': 'integer', 'description': 'Circuit ID'},
@@ -832,16 +968,18 @@ TOOL_DEFINITIONS = {
     },
 
     # ==================== Virtualization Tools ====================
-    'virtualization_list_cluster_types': {
+    # NOTE: Tool names shortened from 'virtualization_' to 'virt_' to meet
+    # 28-char limit (Claude API 64-char limit minus 36-char prefix)
+    'virt_list_cluster_types': {
         'description': 'List all cluster types in NetBox',
         'properties': {'name': {'type': 'string', 'description': 'Filter by name'}}
     },
-    'virtualization_get_cluster_type': {
+    'virt_get_cluster_type': {
         'description': 'Get a specific cluster type by ID',
         'properties': {'id': {'type': 'integer', 'description': 'Cluster type ID'}},
         'required': ['id']
     },
-    'virtualization_create_cluster_type': {
+    'virt_create_cluster_type': {
         'description': 'Create a new cluster type',
         'properties': {
             'name': {'type': 'string', 'description': 'Type name'},
@@ -849,16 +987,16 @@ TOOL_DEFINITIONS = {
         },
         'required': ['name', 'slug']
     },
-    'virtualization_list_cluster_groups': {
+    'virt_list_cluster_groups': {
         'description': 'List all cluster groups in NetBox',
         'properties': {'name': {'type': 'string', 'description': 'Filter by name'}}
     },
-    'virtualization_get_cluster_group': {
+    'virt_get_cluster_group': {
         'description': 'Get a specific cluster group by ID',
         'properties': {'id': {'type': 'integer', 'description': 'Cluster group ID'}},
         'required': ['id']
     },
-    'virtualization_create_cluster_group': {
+    'virt_create_cluster_group': {
         'description': 'Create a new cluster group',
         'properties': {
             'name': {'type': 'string', 'description': 'Group name'},
@@ -866,7 +1004,7 @@ TOOL_DEFINITIONS = {
         },
         'required': ['name', 'slug']
     },
-    'virtualization_list_clusters': {
+    'virt_list_clusters': {
         'description': 'List all clusters in NetBox',
         'properties': {
             'name': {'type': 'string', 'description': 'Filter by name'},
@@ -875,12 +1013,12 @@ TOOL_DEFINITIONS = {
             'site_id': {'type': 'integer', 'description': 'Filter by site ID'}
         }
     },
-    'virtualization_get_cluster': {
+    'virt_get_cluster': {
         'description': 'Get a specific cluster by ID',
         'properties': {'id': {'type': 'integer', 'description': 'Cluster ID'}},
         'required': ['id']
     },
-    'virtualization_create_cluster': {
+    'virt_create_cluster': {
         'description': 'Create a new cluster',
         'properties': {
             'name': {'type': 'string', 'description': 'Cluster name'},
@@ -891,17 +1029,27 @@ TOOL_DEFINITIONS = {
         },
         'required': ['name', 'type']
     },
-    'virtualization_update_cluster': {
+    'virt_update_cluster': {
         'description': 'Update an existing cluster',
-        'properties': {'id': {'type': 'integer', 'description': 'Cluster ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'Cluster ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'type': {'type': 'integer', 'description': 'Cluster type ID'},
+            'group': {'type': 'integer', 'description': 'Cluster group ID'},
+            'site': {'type': 'integer', 'description': 'Site ID'},
+            'status': {'type': 'string', 'description': 'Status'},
+            'tenant': {'type': 'integer', 'description': 'Tenant ID'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
+        },
         'required': ['id']
     },
-    'virtualization_delete_cluster': {
+    'virt_delete_cluster': {
         'description': 'Delete a cluster',
         'properties': {'id': {'type': 'integer', 'description': 'Cluster ID'}},
         'required': ['id']
     },
-    'virtualization_list_virtual_machines': {
+    'virt_list_vms': {
         'description': 'List all virtual machines in NetBox',
         'properties': {
             'name': {'type': 'string', 'description': 'Filter by name'},
@@ -910,12 +1058,12 @@ TOOL_DEFINITIONS = {
             'status': {'type': 'string', 'description': 'Filter by status'}
         }
     },
-    'virtualization_get_virtual_machine': {
+    'virt_get_vm': {
         'description': 'Get a specific virtual machine by ID',
         'properties': {'id': {'type': 'integer', 'description': 'VM ID'}},
         'required': ['id']
     },
-    'virtualization_create_virtual_machine': {
+    'virt_create_vm': {
         'description': 'Create a new virtual machine',
         'properties': {
             'name': {'type': 'string', 'description': 'VM name'},
@@ -928,29 +1076,45 @@ TOOL_DEFINITIONS = {
         },
         'required': ['name']
     },
-    'virtualization_update_virtual_machine': {
+    'virt_update_vm': {
         'description': 'Update an existing virtual machine',
-        'properties': {'id': {'type': 'integer', 'description': 'VM ID'}},
+        'properties': {
+            'id': {'type': 'integer', 'description': 'VM ID'},
+            'name': {'type': 'string', 'description': 'New name'},
+            'status': {'type': 'string', 'description': 'Status'},
+            'cluster': {'type': 'integer', 'description': 'Cluster ID'},
+            'site': {'type': 'integer', 'description': 'Site ID'},
+            'role': {'type': 'integer', 'description': 'Role ID'},
+            'tenant': {'type': 'integer', 'description': 'Tenant ID'},
+            'platform': {'type': 'integer', 'description': 'Platform ID'},
+            'vcpus': {'type': 'number', 'description': 'Number of vCPUs'},
+            'memory': {'type': 'integer', 'description': 'Memory in MB'},
+            'disk': {'type': 'integer', 'description': 'Disk in GB'},
+            'primary_ip4': {'type': 'integer', 'description': 'Primary IPv4 address ID'},
+            'primary_ip6': {'type': 'integer', 'description': 'Primary IPv6 address ID'},
+            'description': {'type': 'string', 'description': 'Description'},
+            'comments': {'type': 'string', 'description': 'Comments'}
+        },
         'required': ['id']
     },
-    'virtualization_delete_virtual_machine': {
+    'virt_delete_vm': {
         'description': 'Delete a virtual machine',
         'properties': {'id': {'type': 'integer', 'description': 'VM ID'}},
         'required': ['id']
     },
-    'virtualization_list_vm_interfaces': {
+    'virt_list_vm_ifaces': {
         'description': 'List all VM interfaces in NetBox',
         'properties': {
             'virtual_machine_id': {'type': 'integer', 'description': 'Filter by VM ID'},
             'name': {'type': 'string', 'description': 'Filter by name'}
         }
     },
-    'virtualization_get_vm_interface': {
+    'virt_get_vm_iface': {
         'description': 'Get a specific VM interface by ID',
         'properties': {'id': {'type': 'integer', 'description': 'Interface ID'}},
         'required': ['id']
     },
-    'virtualization_create_vm_interface': {
+    'virt_create_vm_iface': {
         'description': 'Create a new VM interface',
         'properties': {
             'virtual_machine': {'type': 'integer', 'description': 'VM ID'},
@@ -1088,16 +1252,18 @@ TOOL_DEFINITIONS = {
     },
 
     # ==================== Wireless Tools ====================
-    'wireless_list_wireless_lan_groups': {
+    # NOTE: Tool names shortened from 'wireless_' to 'wlan_' to meet
+    # 28-char limit (Claude API 64-char limit minus 36-char prefix)
+    'wlan_list_groups': {
         'description': 'List all wireless LAN groups in NetBox',
         'properties': {'name': {'type': 'string', 'description': 'Filter by name'}}
     },
-    'wireless_get_wireless_lan_group': {
+    'wlan_get_group': {
         'description': 'Get a specific wireless LAN group by ID',
         'properties': {'id': {'type': 'integer', 'description': 'WLAN group ID'}},
         'required': ['id']
     },
-    'wireless_create_wireless_lan_group': {
+    'wlan_create_group': {
         'description': 'Create a new wireless LAN group',
         'properties': {
             'name': {'type': 'string', 'description': 'Group name'},
@@ -1105,7 +1271,7 @@ TOOL_DEFINITIONS = {
         },
         'required': ['name', 'slug']
     },
-    'wireless_list_wireless_lans': {
+    'wlan_list_lans': {
         'description': 'List all wireless LANs in NetBox',
         'properties': {
             'ssid': {'type': 'string', 'description': 'Filter by SSID'},
@@ -1113,12 +1279,12 @@ TOOL_DEFINITIONS = {
             'status': {'type': 'string', 'description': 'Filter by status'}
         }
     },
-    'wireless_get_wireless_lan': {
+    'wlan_get_lan': {
         'description': 'Get a specific wireless LAN by ID',
         'properties': {'id': {'type': 'integer', 'description': 'WLAN ID'}},
         'required': ['id']
     },
-    'wireless_create_wireless_lan': {
+    'wlan_create_lan': {
         'description': 'Create a new wireless LAN',
         'properties': {
             'ssid': {'type': 'string', 'description': 'SSID'},
@@ -1128,14 +1294,14 @@ TOOL_DEFINITIONS = {
         },
         'required': ['ssid']
     },
-    'wireless_list_wireless_links': {
+    'wlan_list_links': {
         'description': 'List all wireless links in NetBox',
         'properties': {
             'ssid': {'type': 'string', 'description': 'Filter by SSID'},
             'status': {'type': 'string', 'description': 'Filter by status'}
         }
     },
-    'wireless_get_wireless_link': {
+    'wlan_get_link': {
         'description': 'Get a specific wireless link by ID',
         'properties': {'id': {'type': 'integer', 'description': 'Link ID'}},
         'required': ['id']
@@ -1241,6 +1407,52 @@ TOOL_DEFINITIONS = {
 }
 
 
+# Map shortened tool names to (category, method_name) for routing.
+# This is necessary because tool names were shortened to meet the 28-character
+# limit imposed by Claude API's 64-character tool name limit minus the
+# 36-character prefix used by Claude Code for MCP tools.
+TOOL_NAME_MAP = {
+    # Virtualization tools (virt_ -> virtualization category)
+    'virt_list_cluster_types': ('virtualization', 'list_cluster_types'),
+    'virt_get_cluster_type': ('virtualization', 'get_cluster_type'),
+    'virt_create_cluster_type': ('virtualization', 'create_cluster_type'),
+    'virt_list_cluster_groups': ('virtualization', 'list_cluster_groups'),
+    'virt_get_cluster_group': ('virtualization', 'get_cluster_group'),
+    'virt_create_cluster_group': ('virtualization', 'create_cluster_group'),
+    'virt_list_clusters': ('virtualization', 'list_clusters'),
+    'virt_get_cluster': ('virtualization', 'get_cluster'),
+    'virt_create_cluster': ('virtualization', 'create_cluster'),
+    'virt_update_cluster': ('virtualization', 'update_cluster'),
+    'virt_delete_cluster': ('virtualization', 'delete_cluster'),
+    'virt_list_vms': ('virtualization', 'list_virtual_machines'),
+    'virt_get_vm': ('virtualization', 'get_virtual_machine'),
+    'virt_create_vm': ('virtualization', 'create_virtual_machine'),
+    'virt_update_vm': ('virtualization', 'update_virtual_machine'),
+    'virt_delete_vm': ('virtualization', 'delete_virtual_machine'),
+    'virt_list_vm_ifaces': ('virtualization', 'list_vm_interfaces'),
+    'virt_get_vm_iface': ('virtualization', 'get_vm_interface'),
+    'virt_create_vm_iface': ('virtualization', 'create_vm_interface'),
+
+    # Circuits tools (circ_ -> circuits category, for shortened names only)
+    'circ_list_types': ('circuits', 'list_circuit_types'),
+    'circ_get_type': ('circuits', 'get_circuit_type'),
+    'circ_create_type': ('circuits', 'create_circuit_type'),
+    'circ_list_terminations': ('circuits', 'list_circuit_terminations'),
+    'circ_get_termination': ('circuits', 'get_circuit_termination'),
+    'circ_create_termination': ('circuits', 'create_circuit_termination'),
+
+    # Wireless tools (wlan_ -> wireless category)
+    'wlan_list_groups': ('wireless', 'list_wireless_lan_groups'),
+    'wlan_get_group': ('wireless', 'get_wireless_lan_group'),
+    'wlan_create_group': ('wireless', 'create_wireless_lan_group'),
+    'wlan_list_lans': ('wireless', 'list_wireless_lans'),
+    'wlan_get_lan': ('wireless', 'get_wireless_lan'),
+    'wlan_create_lan': ('wireless', 'create_wireless_lan'),
+    'wlan_list_links': ('wireless', 'list_wireless_links'),
+    'wlan_get_link': ('wireless', 'get_wireless_link'),
+}
+
+
 class NetBoxMCPServer:
     """MCP Server for NetBox integration"""
 
@@ -1314,12 +1526,21 @@ class NetBoxMCPServer:
                 )]
 
     async def _route_tool(self, name: str, arguments: dict):
-        """Route tool call to appropriate handler."""
-        parts = name.split('_', 1)
-        if len(parts) != 2:
-            raise ValueError(f"Invalid tool name format: {name}")
+        """Route tool call to appropriate handler.
 
-        category, method_name = parts[0], parts[1]
+        Tool names may be shortened (e.g., 'virt_list_vms' instead of
+        'virtualization_list_virtual_machines') to meet the 28-character
+        limit. TOOL_NAME_MAP handles the translation to actual method names.
+        """
+        # Check if this is a mapped short name
+        if name in TOOL_NAME_MAP:
+            category, method_name = TOOL_NAME_MAP[name]
+        else:
+            # Fall back to original logic for unchanged tools
+            parts = name.split('_', 1)
+            if len(parts) != 2:
+                raise ValueError(f"Invalid tool name format: {name}")
+            category, method_name = parts[0], parts[1]
 
         # Map category to tool class
         tool_map = {

plugins/claude-config-maintainer/hooks/enforce-rules.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+# claude-config-maintainer: enforce mandatory behavior rules
+# Checks if CLAUDE.md has the rules, adds them if missing
+
+PREFIX="[claude-config-maintainer]"
+
+# Find CLAUDE.md in current directory or parent
+CLAUDE_MD=""
+if [ -f "./CLAUDE.md" ]; then
+    CLAUDE_MD="./CLAUDE.md"
+elif [ -f "../CLAUDE.md" ]; then
+    CLAUDE_MD="../CLAUDE.md"
+fi
+
+# If no CLAUDE.md found, exit silently
+if [ -z "$CLAUDE_MD" ]; then
+    exit 0
+fi
+
+# Check if mandatory rules exist
+if grep -q "MANDATORY BEHAVIOR RULES" "$CLAUDE_MD" 2>/dev/null; then
+    # Rules exist, all good
+    exit 0
+fi
+
+# Rules missing - add them
+RULES='## ⛔ MANDATORY BEHAVIOR RULES - READ FIRST
+
+**These rules are NON-NEGOTIABLE. Violating them wastes the user'\''s time and money.**
+
+### 1. WHEN USER ASKS YOU TO CHECK SOMETHING - CHECK EVERYTHING
+- Search ALL locations, not just where you think it is
+- Check cache directories: `~/.claude/plugins/cache/`
+- Check installed: `~/.claude/plugins/marketplaces/`
+- Check source directories
+- **NEVER say "no" or "that'\''s not the issue" without exhaustive verification**
+
+### 2. WHEN USER SAYS SOMETHING IS WRONG - BELIEVE THEM
+- The user knows their system better than you
+- Investigate thoroughly before disagreeing
+- **Your confidence is often wrong. User'\''s instincts are often right.**
+
+### 3. NEVER SAY "DONE" WITHOUT VERIFICATION
+- Run the actual command/script to verify
+- Show the output to the user
+- **"Done" means VERIFIED WORKING, not "I made changes"**
+
+### 4. SHOW EXACTLY WHAT USER ASKS FOR
+- If user asks for messages, show the MESSAGES
+- If user asks for code, show the CODE
+- **Do not interpret or summarize unless asked**
+
+**FAILURE TO FOLLOW THESE RULES = WASTED USER TIME = UNACCEPTABLE**
+
+---
+
+'
+
+# Create temp file with rules + existing content
+{
+    head -1 "$CLAUDE_MD"
+    echo ""
+    echo "$RULES"
+    tail -n +2 "$CLAUDE_MD"
+} > "${CLAUDE_MD}.tmp"
+
+mv "${CLAUDE_MD}.tmp" "$CLAUDE_MD"
+echo "$PREFIX Added mandatory behavior rules to CLAUDE.md"

plugins/claude-config-maintainer/hooks/hooks.json

@@ -0,0 +1,10 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "type": "command",
+        "command": "${CLAUDE_PLUGIN_ROOT}/hooks/enforce-rules.sh"
+      }
+    ]
+  }
+}

plugins/cmdb-assistant/README.md

@@ -111,6 +111,7 @@ cmdb-assistant/
 │   └── plugin.json          # Plugin manifest
 ├── .mcp.json                 # MCP server configuration
 ├── commands/
+│   ├── initial-setup.md     # Setup wizard
 │   ├── cmdb-search.md       # Search command
 │   ├── cmdb-device.md       # Device management
 │   ├── cmdb-ip.md           # IP management

plugins/cmdb-assistant/commands/initial-setup.md

@@ -70,13 +70,15 @@ cat ~/.config/claude/netbox.env 2>/dev/null || echo "FILE_NOT_FOUND"
 ### Step 3.3: Gather NetBox Information
 
 Use AskUserQuestion:
-- Question: "What is your NetBox server URL? (e.g., https://netbox.company.com)"
+- Question: "What is your NetBox API URL? (e.g., https://netbox.company.com/api)"
 - Header: "NetBox URL"
 - Options:
   - "Other (I'll provide the URL)"
 
 Ask user to provide the URL.
 
+**Important:** The URL must include `/api` at the end. If the user provides a URL without `/api`, append it automatically.
+
 ### Step 3.4: Create Configuration File
 
 ```bash
@@ -120,9 +122,11 @@ Use AskUserQuestion:
 ### Step 4.1: Test Configuration (if token was added)
 
 ```bash
-source ~/.config/claude/netbox.env && curl -s -o /dev/null -w "%{http_code}" -H "Authorization: Token $NETBOX_API_TOKEN" "$NETBOX_API_URL/api/"
+source ~/.config/claude/netbox.env && curl -s -o /dev/null -w "%{http_code}" -H "Authorization: Token $NETBOX_API_TOKEN" "$NETBOX_API_URL/"
 ```
 
+**Note:** The URL already includes `/api`, so we just append `/` for the root API endpoint.
+
 Report result:
 - 200: Success
 - 403: Invalid token

plugins/code-sentinel/.claude-plugin/plugin.json

@@ -9,5 +9,6 @@
   "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/code-sentinel/README.md",
   "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
   "license": "MIT",
-  "keywords": ["security", "refactoring", "code-quality", "static-analysis", "hooks"]
+  "keywords": ["security", "refactoring", "code-quality", "static-analysis", "hooks"],
+  "commands": ["./commands/"]
 }

plugins/code-sentinel/hooks/hooks.json

@@ -5,8 +5,8 @@
         "matcher": "Write|Edit|MultiEdit",
         "hooks": [
           {
-            "type": "prompt",
-            "prompt": "[code-sentinel] SECURITY CHECK - Before writing this code, scan for these patterns:\n\n**Critical (BLOCK if found):**\n- eval(), exec() with user input\n- SQL string concatenation (SQL injection)\n- shell=True with user input (command injection)\n- Hardcoded secrets (API keys, passwords, tokens)\n- Pickle/marshal deserialization of untrusted data\n- innerHTML/dangerouslySetInnerHTML with user content (XSS)\n\n**Warning (WARN but allow):**\n- subprocess without input validation\n- File operations without path sanitization\n- HTTP requests without timeout\n- Broad exception catches (except:)\n- Debug/print statements with sensitive data\n\n**Response:**\n- If CRITICAL found: STOP with '[code-sentinel] BLOCKED:', explain the issue, suggest safe alternative\n- If WARNING found: Note briefly with '[code-sentinel] WARNING:', proceed with suggestion\n- If clean: Proceed silently (say nothing)\n\nDo NOT announce clean scans. Only speak if issues found."
+            "type": "command",
+            "command": "${CLAUDE_PLUGIN_ROOT}/hooks/security-check.sh"
           }
         ]
       }

plugins/code-sentinel/hooks/security-check.sh

@@ -0,0 +1,62 @@
+#!/bin/bash
+# code-sentinel security check hook
+# Checks for obvious security issues in code files, skips config/docs
+# Command hook - guaranteed predictable behavior
+
+# Read tool input from stdin
+INPUT=$(cat)
+
+# Extract file_path from JSON input
+FILE_PATH=$(echo "$INPUT" | grep -o '"file_path"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"file_path"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
+
+# If no file_path, exit silently
+if [ -z "$FILE_PATH" ]; then
+    exit 0
+fi
+
+# SKIP config/doc files entirely - exit silently
+case "$FILE_PATH" in
+    *.md|*.json|*.yml|*.yaml|*.txt|*.toml|*.ini|*.cfg|*.conf)
+        exit 0
+        ;;
+    */docs/*|*/README*|*/CHANGELOG*|*/LICENSE*)
+        exit 0
+        ;;
+    */.claude/*|*/.github/*|*/.vscode/*)
+        exit 0
+        ;;
+esac
+
+# For code files, extract content to check
+# For Edit tool: check new_string
+# For Write tool: check content
+CONTENT=$(echo "$INPUT" | grep -o '"new_string"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"new_string"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
+if [ -z "$CONTENT" ]; then
+    CONTENT=$(echo "$INPUT" | grep -o '"content"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"content"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
+fi
+
+# If no content to check, exit silently
+if [ -z "$CONTENT" ]; then
+    exit 0
+fi
+
+# Check for hardcoded secrets patterns (obvious cases only)
+if echo "$CONTENT" | grep -qiE '(api[_-]?key|api[_-]?secret|password|passwd|secret[_-]?key|auth[_-]?token)[[:space:]]*[=:][[:space:]]*["\x27][A-Za-z0-9+/=_-]{20,}["\x27]'; then
+    echo "[code-sentinel] BLOCKED: Hardcoded secret detected"
+    exit 1
+fi
+
+# Check for AWS keys pattern
+if echo "$CONTENT" | grep -qE 'AKIA[A-Z0-9]{16}'; then
+    echo "[code-sentinel] BLOCKED: AWS access key detected"
+    exit 1
+fi
+
+# Check for private key headers
+if echo "$CONTENT" | grep -qE '\-\-\-\-\-BEGIN (RSA |DSA |EC |OPENSSH )?PRIVATE KEY\-\-\-\-\-'; then
+    echo "[code-sentinel] BLOCKED: Private key detected"
+    exit 1
+fi
+
+# All other cases: exit silently (allow the edit)
+exit 0

plugins/data-platform/.claude-plugin/plugin.json

@@ -0,0 +1,25 @@
+{
+  "name": "data-platform",
+  "version": "1.0.0",
+  "description": "Data engineering tools with pandas, PostgreSQL/PostGIS, and dbt integration",
+  "author": {
+    "name": "Leo Miranda",
+    "email": "leobmiranda@gmail.com"
+  },
+  "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/data-platform/README.md",
+  "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
+  "license": "MIT",
+  "keywords": [
+    "pandas",
+    "postgresql",
+    "postgis",
+    "dbt",
+    "data-engineering",
+    "etl",
+    "dataframe"
+  ],
+  "hooks": "hooks/hooks.json",
+  "commands": ["./commands/"],
+  "agents": ["./agents/"],
+  "mcpServers": ["./.mcp.json"]
+}

plugins/data-platform/.mcp.json

@@ -0,0 +1,10 @@
+{
+  "mcpServers": {
+    "data-platform": {
+      "type": "stdio",
+      "command": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/data-platform/.venv/bin/python",
+      "args": ["-m", "mcp_server.server"],
+      "cwd": "${CLAUDE_PLUGIN_ROOT}/mcp-servers/data-platform"
+    }
+  }
+}

plugins/data-platform/README.md

@@ -0,0 +1,119 @@
+# data-platform Plugin
+
+Data engineering tools with pandas, PostgreSQL/PostGIS, and dbt integration for Claude Code.
+
+## Features
+
+- **pandas Operations**: Load, transform, and export DataFrames with persistent data_ref system
+- **PostgreSQL/PostGIS**: Database queries with connection pooling and spatial data support
+- **dbt Integration**: Build tool wrapper with pre-execution validation
+
+## Installation
+
+This plugin is part of the leo-claude-mktplace. Install via:
+
+```bash
+# From marketplace
+claude plugins install leo-claude-mktplace/data-platform
+
+# Setup MCP server venv
+cd ~/.claude/plugins/marketplaces/leo-claude-mktplace/mcp-servers/data-platform
+python -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+```
+
+## Configuration
+
+### PostgreSQL (Optional)
+
+Create `~/.config/claude/postgres.env`:
+
+```env
+POSTGRES_URL=postgresql://user:password@host:5432/database
+```
+
+### dbt (Optional)
+
+Add to project `.env`:
+
+```env
+DBT_PROJECT_DIR=/path/to/dbt/project
+DBT_PROFILES_DIR=~/.dbt
+```
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `/initial-setup` | Interactive setup wizard for PostgreSQL and dbt configuration |
+| `/ingest` | Load data from files or database |
+| `/profile` | Generate data profile and statistics |
+| `/schema` | Show database/DataFrame schema |
+| `/explain` | Explain dbt model lineage |
+| `/lineage` | Visualize data dependencies |
+| `/run` | Execute dbt models |
+
+## Agents
+
+| Agent | Description |
+|-------|-------------|
+| `data-ingestion` | Data loading and transformation specialist |
+| `data-analysis` | Exploration and profiling specialist |
+
+## data_ref System
+
+All DataFrame operations use a `data_ref` system for persistence:
+
+```
+# Load returns a reference
+read_csv("data.csv") → {"data_ref": "sales_data"}
+
+# Use reference in subsequent operations
+filter("sales_data", "amount > 100") → {"data_ref": "sales_data_filtered"}
+describe("sales_data_filtered") → {statistics}
+```
+
+## Example Workflow
+
+```
+/ingest data/sales.csv
+# → Loaded 50,000 rows as "sales_data"
+
+/profile sales_data
+# → Statistical summary, null counts, quality assessment
+
+/schema orders
+# → Column names, types, constraints
+
+/lineage fct_orders
+# → Dependency graph showing upstream/downstream models
+
+/run dim_customers
+# → Pre-validates then executes dbt model
+```
+
+## Tools Summary
+
+### pandas (14 tools)
+`read_csv`, `read_parquet`, `read_json`, `to_csv`, `to_parquet`, `describe`, `head`, `tail`, `filter`, `select`, `groupby`, `join`, `list_data`, `drop_data`
+
+### PostgreSQL (6 tools)
+`pg_connect`, `pg_query`, `pg_execute`, `pg_tables`, `pg_columns`, `pg_schemas`
+
+### PostGIS (4 tools)
+`st_tables`, `st_geometry_type`, `st_srid`, `st_extent`
+
+### dbt (8 tools)
+`dbt_parse`, `dbt_run`, `dbt_test`, `dbt_build`, `dbt_compile`, `dbt_ls`, `dbt_docs_generate`, `dbt_lineage`
+
+## Memory Management
+
+- Default limit: 100,000 rows per DataFrame
+- Configure via `DATA_PLATFORM_MAX_ROWS` environment variable
+- Use `chunk_size` parameter for large files
+- Monitor with `list_data` tool
+
+## SessionStart Hook
+
+On session start, the plugin checks PostgreSQL connectivity and displays a warning if unavailable. This is non-blocking - pandas and dbt tools remain available.

plugins/data-platform/agents/data-analysis.md

@@ -0,0 +1,98 @@
+# Data Analysis Agent
+
+You are a data analysis specialist. Your role is to help users explore, profile, and understand their data.
+
+## Capabilities
+
+- Profile datasets with statistical summaries
+- Explore database schemas and structures
+- Analyze dbt model lineage and dependencies
+- Provide data quality assessments
+- Generate insights and recommendations
+
+## Available Tools
+
+### Data Exploration
+- `describe` - Statistical summary
+- `head` - Preview first rows
+- `tail` - Preview last rows
+- `list_data` - List available DataFrames
+
+### Database Exploration
+- `pg_connect` - Check database connection
+- `pg_tables` - List all tables
+- `pg_columns` - Get column details
+- `pg_schemas` - List schemas
+
+### PostGIS Exploration
+- `st_tables` - List spatial tables
+- `st_geometry_type` - Get geometry type
+- `st_srid` - Get coordinate system
+- `st_extent` - Get bounding box
+
+### dbt Analysis
+- `dbt_lineage` - Model dependencies
+- `dbt_ls` - List resources
+- `dbt_compile` - View compiled SQL
+- `dbt_docs_generate` - Generate docs
+
+## Workflow Guidelines
+
+1. **Understand the question**:
+   - What does the user want to know?
+   - What data is available?
+   - What level of detail is needed?
+
+2. **Explore the data**:
+   - Start with `list_data` or `pg_tables`
+   - Get schema info with `describe` or `pg_columns`
+   - Preview with `head` to understand content
+
+3. **Profile thoroughly**:
+   - Use `describe` for statistics
+   - Check for nulls, outliers, patterns
+   - Note data quality issues
+
+4. **Analyze dependencies** (for dbt):
+   - Use `dbt_lineage` to trace data flow
+   - Understand transformations
+   - Identify critical paths
+
+5. **Provide insights**:
+   - Summarize findings clearly
+   - Highlight potential issues
+   - Recommend next steps
+
+## Analysis Patterns
+
+### Data Quality Check
+1. `describe` - Get statistics
+2. Check null percentages
+3. Identify outliers (min/max vs mean)
+4. Flag suspicious patterns
+
+### Schema Comparison
+1. `pg_columns` - Get table A schema
+2. `pg_columns` - Get table B schema
+3. Compare column names, types
+4. Identify mismatches
+
+### Lineage Analysis
+1. `dbt_lineage` - Get model graph
+2. Trace upstream sources
+3. Identify downstream impact
+4. Document critical path
+
+## Example Interactions
+
+**User**: What's in the sales_data DataFrame?
+**Agent**: Uses `describe`, `head`, explains columns, statistics, patterns
+
+**User**: What tables are in the database?
+**Agent**: Uses `pg_tables`, shows list with column counts
+
+**User**: How does the dim_customers model work?
+**Agent**: Uses `dbt_lineage`, `dbt_compile`, explains dependencies and SQL
+
+**User**: Is there any spatial data?
+**Agent**: Uses `st_tables`, shows PostGIS tables with geometry types

plugins/data-platform/agents/data-ingestion.md

@@ -0,0 +1,81 @@
+# Data Ingestion Agent
+
+You are a data ingestion specialist. Your role is to help users load, transform, and prepare data for analysis.
+
+## Capabilities
+
+- Load data from CSV, Parquet, JSON files
+- Query PostgreSQL databases
+- Transform data using filter, select, groupby, join operations
+- Export data to various formats
+- Handle large datasets with chunking
+
+## Available Tools
+
+### File Operations
+- `read_csv` - Load CSV files with optional chunking
+- `read_parquet` - Load Parquet files
+- `read_json` - Load JSON/JSONL files
+- `to_csv` - Export to CSV
+- `to_parquet` - Export to Parquet
+
+### Data Transformation
+- `filter` - Filter rows by condition
+- `select` - Select specific columns
+- `groupby` - Group and aggregate
+- `join` - Join two DataFrames
+
+### Database Operations
+- `pg_query` - Execute SELECT queries
+- `pg_execute` - Execute INSERT/UPDATE/DELETE
+- `pg_tables` - List available tables
+
+### Management
+- `list_data` - List all stored DataFrames
+- `drop_data` - Remove DataFrame from store
+
+## Workflow Guidelines
+
+1. **Understand the data source**:
+   - Ask about file location/format
+   - For database, understand table structure
+   - Clarify any filters or transformations needed
+
+2. **Load data efficiently**:
+   - Use appropriate reader for file format
+   - For large files (>100k rows), use chunking
+   - Name DataFrames meaningfully
+
+3. **Transform as needed**:
+   - Apply filters early to reduce data size
+   - Select only needed columns
+   - Join related datasets
+
+4. **Validate results**:
+   - Check row counts after transformations
+   - Verify data types are correct
+   - Preview results with `head`
+
+5. **Store with meaningful names**:
+   - Use descriptive data_ref names
+   - Document the source and transformations
+
+## Memory Management
+
+- Default row limit: 100,000 rows
+- For larger datasets, suggest:
+  - Filtering before loading
+  - Using chunk_size parameter
+  - Aggregating to reduce size
+  - Storing to Parquet for efficient retrieval
+
+## Example Interactions
+
+**User**: Load the sales data from data/sales.csv
+**Agent**: Uses `read_csv` to load, reports data_ref, row count, columns
+
+**User**: Filter to only Q4 2024 sales
+**Agent**: Uses `filter` with date condition, stores filtered result
+
+**User**: Join with customer data
+**Agent**: Uses `join` to combine, validates result counts

plugins/data-platform/claude-md-integration.md

@@ -0,0 +1,90 @@
+# data-platform Plugin - CLAUDE.md Integration
+
+Add this section to your project's CLAUDE.md to enable data-platform plugin features.
+
+## Suggested CLAUDE.md Section
+
+```markdown
+## Data Platform Integration
+
+This project uses the data-platform plugin for data engineering workflows.
+
+### Configuration
+
+**PostgreSQL**: Credentials in `~/.config/claude/postgres.env`
+**dbt**: Project path auto-detected from `dbt_project.yml`
+
+### Available Commands
+
+| Command | Purpose |
+|---------|---------|
+| `/ingest` | Load data from files or database |
+| `/profile` | Generate statistical profile |
+| `/schema` | Show schema information |
+| `/explain` | Explain dbt model |
+| `/lineage` | Show data lineage |
+| `/run` | Execute dbt models |
+
+### data_ref Convention
+
+DataFrames are stored with references. Use meaningful names:
+- `raw_*` for source data
+- `stg_*` for staged/cleaned data
+- `dim_*` for dimension tables
+- `fct_*` for fact tables
+- `rpt_*` for reports
+
+### dbt Workflow
+
+1. Always validate before running: `/run` includes automatic `dbt_parse`
+2. For dbt 1.9+, check for deprecated syntax before commits
+3. Use `/lineage` to understand impact of changes
+
+### Database Access
+
+PostgreSQL tools require POSTGRES_URL configuration:
+- Read-only queries: `pg_query`
+- Write operations: `pg_execute`
+- Schema exploration: `pg_tables`, `pg_columns`
+
+PostGIS spatial data:
+- List spatial tables: `st_tables`
+- Check geometry: `st_geometry_type`, `st_srid`, `st_extent`
+```
+
+## Environment Variables
+
+Add to project `.env` if needed:
+
+```env
+# dbt configuration
+DBT_PROJECT_DIR=./transform
+DBT_PROFILES_DIR=~/.dbt
+
+# Memory limits
+DATA_PLATFORM_MAX_ROWS=100000
+```
+
+## Typical Workflows
+
+### Data Exploration
+```
+/ingest data/raw_customers.csv
+/profile raw_customers
+/schema
+```
+
+### ETL Development
+```
+/schema orders              # Understand source
+/explain stg_orders         # Understand transformation
+/run stg_orders             # Test the model
+/lineage fct_orders         # Check downstream impact
+```
+
+### Database Analysis
+```
+/schema                     # List all tables
+pg_columns orders           # Detailed schema
+st_tables                   # Find spatial data
+```

plugins/data-platform/commands/explain.md

@@ -0,0 +1,44 @@
+# /explain - dbt Model Explanation
+
+Explain a dbt model's purpose, dependencies, and SQL logic.
+
+## Usage
+
+```
+/explain <model_name>
+```
+
+## Workflow
+
+1. **Get model info**:
+   - Use `dbt_lineage` to get model metadata
+   - Extract description, tags, materialization
+
+2. **Analyze dependencies**:
+   - Show upstream models (what this depends on)
+   - Show downstream models (what depends on this)
+   - Visualize as dependency tree
+
+3. **Compile SQL**:
+   - Use `dbt_compile` to get rendered SQL
+   - Explain key transformations
+
+4. **Report**:
+   - Model purpose (from description)
+   - Materialization strategy
+   - Dependency graph
+   - Key SQL logic explained
+
+## Examples
+
+```
+/explain dim_customers
+/explain fct_orders
+```
+
+## Available Tools
+
+Use these MCP tools:
+- `dbt_lineage` - Get model dependencies
+- `dbt_compile` - Get compiled SQL
+- `dbt_ls` - List related resources

plugins/data-platform/commands/ingest.md

@@ -0,0 +1,44 @@
+# /ingest - Data Ingestion
+
+Load data from files or database into the data platform.
+
+## Usage
+
+```
+/ingest [source]
+```
+
+## Workflow
+
+1. **Identify data source**:
+   - If source is a file path, determine format (CSV, Parquet, JSON)
+   - If source is "db" or a table name, query PostgreSQL
+
+2. **Load data**:
+   - For files: Use `read_csv`, `read_parquet`, or `read_json`
+   - For database: Use `pg_query` with appropriate SELECT
+
+3. **Validate**:
+   - Check row count against limits
+   - If exceeds 100k rows, suggest chunking or filtering
+
+4. **Report**:
+   - Show data_ref, row count, columns, and memory usage
+   - Preview first few rows
+
+## Examples
+
+```
+/ingest data/sales.csv
+/ingest data/customers.parquet
+/ingest "SELECT * FROM orders WHERE created_at > '2024-01-01'"
+```
+
+## Available Tools
+
+Use these MCP tools:
+- `read_csv` - Load CSV files
+- `read_parquet` - Load Parquet files
+- `read_json` - Load JSON/JSONL files
+- `pg_query` - Query PostgreSQL database
+- `list_data` - List loaded DataFrames

plugins/data-platform/commands/initial-setup.md

@@ -0,0 +1,231 @@
+---
+description: Interactive setup wizard for data-platform plugin - configures MCP server and optional PostgreSQL/dbt
+---
+
+# Data Platform Setup Wizard
+
+This command sets up the data-platform plugin with pandas, PostgreSQL, and dbt integration.
+
+## Important Context
+
+- **This command uses Bash, Read, Write, and AskUserQuestion tools** - NOT MCP tools
+- **MCP tools won't work until after setup + session restart**
+- **PostgreSQL and dbt are optional** - pandas tools work without them
+
+---
+
+## Phase 1: Environment Validation
+
+### Step 1.1: Check Python Version
+
+```bash
+python3 --version
+```
+
+Requires Python 3.10+. If below, stop setup and inform user.
+
+### Step 1.2: Check for Required Libraries
+
+```bash
+python3 -c "import sys; print(f'Python {sys.version_info.major}.{sys.version_info.minor}')"
+```
+
+---
+
+## Phase 2: MCP Server Setup
+
+### Step 2.1: Locate Data Platform MCP Server
+
+The MCP server should be at the marketplace root:
+
+```bash
+# If running from installed marketplace
+ls -la ~/.claude/plugins/marketplaces/leo-claude-mktplace/mcp-servers/data-platform/ 2>/dev/null || echo "NOT_FOUND_INSTALLED"
+
+# If running from source
+ls -la ~/claude-plugins-work/mcp-servers/data-platform/ 2>/dev/null || echo "NOT_FOUND_SOURCE"
+```
+
+Determine the correct path based on which exists.
+
+### Step 2.2: Check Virtual Environment
+
+```bash
+ls -la /path/to/mcp-servers/data-platform/.venv/bin/python 2>/dev/null && echo "VENV_EXISTS" || echo "VENV_MISSING"
+```
+
+### Step 2.3: Create Virtual Environment (if missing)
+
+```bash
+cd /path/to/mcp-servers/data-platform && python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip && pip install -r requirements.txt && deactivate
+```
+
+**Note:** This may take a few minutes due to pandas, pyarrow, and dbt dependencies.
+
+---
+
+## Phase 3: PostgreSQL Configuration (Optional)
+
+### Step 3.1: Ask About PostgreSQL
+
+Use AskUserQuestion:
+- Question: "Do you want to configure PostgreSQL database access?"
+- Header: "PostgreSQL"
+- Options:
+  - "Yes, I have a PostgreSQL database"
+  - "No, I'll only use pandas/dbt tools"
+
+**If user chooses "No":** Skip to Phase 4.
+
+### Step 3.2: Create Config Directory
+
+```bash
+mkdir -p ~/.config/claude
+```
+
+### Step 3.3: Check PostgreSQL Configuration
+
+```bash
+cat ~/.config/claude/postgres.env 2>/dev/null || echo "FILE_NOT_FOUND"
+```
+
+**If file exists with valid URL:** Skip to Step 3.6.
+**If missing or has placeholders:** Continue.
+
+### Step 3.4: Gather PostgreSQL Information
+
+Use AskUserQuestion:
+- Question: "What is your PostgreSQL connection URL format?"
+- Header: "DB Format"
+- Options:
+  - "Standard: postgresql://user:pass@host:5432/db"
+  - "PostGIS: postgresql://user:pass@host:5432/db (with PostGIS extension)"
+  - "Other (I'll provide the full URL)"
+
+Ask user to provide the connection URL.
+
+### Step 3.5: Create Configuration File
+
+```bash
+cat > ~/.config/claude/postgres.env << 'EOF'
+# PostgreSQL Configuration
+# Generated by data-platform /initial-setup
+
+POSTGRES_URL=<USER_PROVIDED_URL>
+EOF
+chmod 600 ~/.config/claude/postgres.env
+```
+
+### Step 3.6: Test PostgreSQL Connection (if configured)
+
+```bash
+source ~/.config/claude/postgres.env && python3 -c "
+import asyncio
+import asyncpg
+async def test():
+    try:
+        conn = await asyncpg.connect('$POSTGRES_URL', timeout=5)
+        ver = await conn.fetchval('SELECT version()')
+        await conn.close()
+        print(f'SUCCESS: {ver.split(\",\")[0]}')
+    except Exception as e:
+        print(f'FAILED: {e}')
+asyncio.run(test())
+"
+```
+
+Report result:
+- SUCCESS: Connection works
+- FAILED: Show error and suggest fixes
+
+---
+
+## Phase 4: dbt Configuration (Optional)
+
+### Step 4.1: Ask About dbt
+
+Use AskUserQuestion:
+- Question: "Do you use dbt for data transformations in your projects?"
+- Header: "dbt"
+- Options:
+  - "Yes, I have dbt projects"
+  - "No, I don't use dbt"
+
+**If user chooses "No":** Skip to Phase 5.
+
+### Step 4.2: dbt Discovery
+
+dbt configuration is **project-level** (not system-level). The plugin auto-detects dbt projects by looking for `dbt_project.yml`.
+
+Inform user:
+```
+dbt projects are detected automatically when you work in a directory
+containing dbt_project.yml.
+
+If your dbt project is in a subdirectory, you can set DBT_PROJECT_DIR
+in your project's .env file:
+
+  DBT_PROJECT_DIR=./transform
+  DBT_PROFILES_DIR=~/.dbt
+```
+
+### Step 4.3: Check dbt Installation
+
+```bash
+dbt --version 2>/dev/null || echo "DBT_NOT_FOUND"
+```
+
+**If not found:** Inform user that dbt CLI tools require dbt-core to be installed globally or in the project.
+
+---
+
+## Phase 5: Validation
+
+### Step 5.1: Verify MCP Server
+
+```bash
+cd /path/to/mcp-servers/data-platform && .venv/bin/python -c "from mcp_server.server import DataPlatformMCPServer; print('MCP Server OK')"
+```
+
+### Step 5.2: Summary
+
+```
+╔════════════════════════════════════════════════════════════╗
+║            DATA-PLATFORM SETUP COMPLETE                    ║
+╠════════════════════════════════════════════════════════════╣
+║ MCP Server:        ✓ Ready                                 ║
+║ pandas Tools:      ✓ Available (14 tools)                  ║
+║ PostgreSQL Tools:  [✓/✗] [Status based on config]          ║
+║ PostGIS Tools:     [✓/✗] [Status based on PostGIS]         ║
+║ dbt Tools:         [✓/✗] [Status based on discovery]       ║
+╚════════════════════════════════════════════════════════════╝
+```
+
+### Step 5.3: Session Restart Notice
+
+---
+
+**⚠️ Session Restart Required**
+
+Restart your Claude Code session for MCP tools to become available.
+
+**After restart, you can:**
+- Run `/ingest` to load data from files or database
+- Run `/profile` to analyze DataFrame statistics
+- Run `/schema` to explore database/DataFrame schema
+- Run `/run` to execute dbt models (if configured)
+- Run `/lineage` to view dbt model dependencies
+
+---
+
+## Memory Limits
+
+The data-platform plugin has a default row limit of 100,000 rows per DataFrame. For larger datasets:
+- Use chunked processing (`chunk_size` parameter)
+- Filter data before loading
+- Store to Parquet for efficient re-loading
+
+You can override the limit by setting in your project `.env`:
+```
+DATA_PLATFORM_MAX_ROWS=500000
+```

plugins/data-platform/commands/lineage.md

@@ -0,0 +1,60 @@
+# /lineage - Data Lineage Visualization
+
+Show data lineage for dbt models or database tables.
+
+## Usage
+
+```
+/lineage <model_name> [--depth N]
+```
+
+## Workflow
+
+1. **Get lineage data**:
+   - Use `dbt_lineage` for dbt models
+   - For database tables, trace through dbt manifest
+
+2. **Build lineage graph**:
+   - Identify all upstream sources
+   - Identify all downstream consumers
+   - Note materialization at each node
+
+3. **Visualize**:
+   - ASCII art dependency tree
+   - List format with indentation
+   - Show depth levels
+
+4. **Report**:
+   - Full dependency chain
+   - Critical path identification
+   - Refresh implications
+
+## Examples
+
+```
+/lineage dim_customers
+/lineage fct_orders --depth 3
+```
+
+## Output Format
+
+```
+Sources:
+  └── raw_customers (source)
+  └── raw_orders (source)
+
+dim_customers (table)
+  ├── upstream:
+  │   └── stg_customers (view)
+  │       └── raw_customers (source)
+  └── downstream:
+      └── fct_orders (incremental)
+      └── rpt_customer_lifetime (table)
+```
+
+## Available Tools
+
+Use these MCP tools:
+- `dbt_lineage` - Get model dependencies
+- `dbt_ls` - List dbt resources
+- `dbt_docs_generate` - Generate full manifest

plugins/data-platform/commands/profile.md

@@ -0,0 +1,44 @@
+# /profile - Data Profiling
+
+Generate statistical profile and quality report for a DataFrame.
+
+## Usage
+
+```
+/profile <data_ref>
+```
+
+## Workflow
+
+1. **Get data reference**:
+   - If no data_ref provided, use `list_data` to show available options
+   - Validate the data_ref exists
+
+2. **Generate profile**:
+   - Use `describe` for statistical summary
+   - Analyze null counts, unique values, data types
+
+3. **Quality assessment**:
+   - Identify columns with high null percentage
+   - Flag potential data quality issues
+   - Suggest cleaning operations if needed
+
+4. **Report**:
+   - Summary statistics per column
+   - Data type distribution
+   - Memory usage
+   - Quality score
+
+## Examples
+
+```
+/profile sales_data
+/profile df_a1b2c3d4
+```
+
+## Available Tools
+
+Use these MCP tools:
+- `describe` - Get statistical summary
+- `head` - Preview first rows
+- `list_data` - List available DataFrames

plugins/data-platform/commands/run.md

@@ -0,0 +1,55 @@
+# /run - Execute dbt Models
+
+Run dbt models with automatic pre-validation.
+
+## Usage
+
+```
+/run [model_selection] [--full-refresh]
+```
+
+## Workflow
+
+1. **Pre-validation** (MANDATORY):
+   - Use `dbt_parse` to validate project
+   - Check for deprecated syntax (dbt 1.9+)
+   - If validation fails, show errors and STOP
+
+2. **Execute models**:
+   - Use `dbt_run` with provided selection
+   - Monitor progress and capture output
+
+3. **Report results**:
+   - Success/failure status per model
+   - Execution time
+   - Row counts where available
+   - Any warnings or errors
+
+## Examples
+
+```
+/run                           # Run all models
+/run dim_customers             # Run specific model
+/run +fct_orders               # Run model and its upstream
+/run tag:daily                 # Run models with tag
+/run --full-refresh            # Rebuild incremental models
+```
+
+## Selection Syntax
+
+| Pattern | Meaning |
+|---------|---------|
+| `model_name` | Run single model |
+| `+model_name` | Run model and upstream |
+| `model_name+` | Run model and downstream |
+| `+model_name+` | Run model with all deps |
+| `tag:name` | Run by tag |
+| `path:models/staging` | Run by path |
+
+## Available Tools
+
+Use these MCP tools:
+- `dbt_parse` - Pre-validation (ALWAYS RUN FIRST)
+- `dbt_run` - Execute models
+- `dbt_build` - Run + test
+- `dbt_test` - Run tests only

plugins/data-platform/commands/schema.md

@@ -0,0 +1,48 @@
+# /schema - Schema Exploration
+
+Display schema information for database tables or DataFrames.
+
+## Usage
+
+```
+/schema [table_name | data_ref]
+```
+
+## Workflow
+
+1. **Determine target**:
+   - If argument is a loaded data_ref, show DataFrame schema
+   - If argument is a table name, query database schema
+   - If no argument, list all available tables and DataFrames
+
+2. **For DataFrames**:
+   - Use `describe` to get column info
+   - Show dtypes, null counts, sample values
+
+3. **For database tables**:
+   - Use `pg_columns` for column details
+   - Use `st_tables` to check for PostGIS columns
+   - Show constraints and indexes if available
+
+4. **Report**:
+   - Column name, type, nullable, default
+   - For PostGIS: geometry type, SRID
+   - For DataFrames: pandas dtype, null percentage
+
+## Examples
+
+```
+/schema                    # List all tables and DataFrames
+/schema customers          # Show table schema
+/schema sales_data         # Show DataFrame schema
+```
+
+## Available Tools
+
+Use these MCP tools:
+- `pg_tables` - List database tables
+- `pg_columns` - Get column info
+- `pg_schemas` - List schemas
+- `st_tables` - List PostGIS tables
+- `describe` - Get DataFrame info
+- `list_data` - List DataFrames

plugins/data-platform/hooks/hooks.json

@@ -0,0 +1,10 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "type": "command",
+        "command": "${CLAUDE_PLUGIN_ROOT}/hooks/startup-check.sh"
+      }
+    ]
+  }
+}

plugins/data-platform/hooks/startup-check.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+# data-platform startup check hook
+# Checks for common issues at session start
+# All output MUST have [data-platform] prefix
+
+PREFIX="[data-platform]"
+
+# Check if MCP venv exists
+PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "$(realpath "$0")")")}"
+VENV_PATH="$PLUGIN_ROOT/mcp-servers/data-platform/.venv/bin/python"
+
+if [[ ! -f "$VENV_PATH" ]]; then
+    echo "$PREFIX MCP venv missing - run /initial-setup or setup.sh"
+    exit 0
+fi
+
+# Check PostgreSQL configuration (optional - just warn if configured but failing)
+POSTGRES_CONFIG="$HOME/.config/claude/postgres.env"
+if [[ -f "$POSTGRES_CONFIG" ]]; then
+    source "$POSTGRES_CONFIG"
+    if [[ -n "${POSTGRES_URL:-}" ]]; then
+        # Quick connection test (5 second timeout)
+        RESULT=$("$VENV_PATH" -c "
+import asyncio
+import sys
+async def test():
+    try:
+        import asyncpg
+        conn = await asyncpg.connect('$POSTGRES_URL', timeout=5)
+        await conn.close()
+        return 'OK'
+    except Exception as e:
+        return f'FAIL: {e}'
+print(asyncio.run(test()))
+" 2>/dev/null || echo "FAIL: asyncpg not installed")
+
+        if [[ "$RESULT" == "OK" ]]; then
+            # PostgreSQL OK - say nothing
+            :
+        elif [[ "$RESULT" == *"FAIL"* ]]; then
+            echo "$PREFIX PostgreSQL connection failed - check POSTGRES_URL"
+        fi
+    fi
+fi
+
+# Check dbt project (if in a project with dbt_project.yml)
+if [[ -f "dbt_project.yml" ]] || [[ -f "transform/dbt_project.yml" ]]; then
+    if ! command -v dbt &> /dev/null; then
+        echo "$PREFIX dbt CLI not found - dbt tools unavailable"
+    fi
+fi
+
+# All checks passed - say nothing
+exit 0

plugins/data-platform/mcp-servers/data-platform

@@ -0,0 +1 @@
+../../../mcp-servers/data-platform

plugins/doc-guardian/.claude-plugin/plugin.json

@@ -9,5 +9,6 @@
   "homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/doc-guardian/README.md",
   "repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
   "license": "MIT",
-  "keywords": ["documentation", "sync", "drift-detection", "automation", "hooks"]
+  "keywords": ["documentation", "sync", "drift-detection", "automation", "hooks"],
+  "commands": ["./commands/"]
 }

plugins/doc-guardian/hooks/hooks.json

@@ -5,8 +5,8 @@
         "matcher": "Write|Edit|MultiEdit",
         "hooks": [
           {
-            "type": "prompt",
-            "prompt": "[doc-guardian] QUICK drift check (DO NOT block workflow):\n\n1. ONLY check if the modified file is referenced in README.md, CLAUDE.md, or API docs in the SAME directory\n2. Do NOT read files or perform deep analysis - just note potential drift based on file name/path\n3. If potential drift: output a single line like '[doc-guardian] Note: {filename} changed - may affect {doc}. Run /doc-sync to verify.'\n4. If no obvious drift: say nothing\n\nIMPORTANT: This is notification-only. Do NOT read documentation files, do NOT make changes, do NOT use any tools. Just a quick mental check based on the file path."
+            "type": "command",
+            "command": "${CLAUDE_PLUGIN_ROOT}/hooks/notify.sh"
           }
         ]
       }

plugins/doc-guardian/hooks/notify.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+# doc-guardian notification hook
+# Outputs a single notification for config file changes, nothing otherwise
+# This is a command hook - guaranteed not to block workflow
+
+# Read tool input from stdin (JSON with file_path)
+INPUT=$(cat)
+
+# Extract file_path from JSON input
+FILE_PATH=$(echo "$INPUT" | grep -o '"file_path"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"file_path"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
+
+# If no file_path found, exit silently
+if [ -z "$FILE_PATH" ]; then
+    exit 0
+fi
+
+# Check if file is in a config directory (commands/, agents/, skills/, hooks/)
+if echo "$FILE_PATH" | grep -qE '/(commands|agents|skills|hooks)/'; then
+    echo "[doc-guardian] Config file modified. Run /doc-sync when ready."
+fi
+
+# Exit silently for all other files (no output = no blocking)
+exit 0

plugins/git-flow/README.md

@@ -10,7 +10,7 @@ git-flow streamlines common git operations with smart defaults, conventional com
 
 | Command | Description |
 |---------|-------------|
-| `/commit` | Create commit with auto-generated conventional message |
+| `/commit` | Create commit with auto-generated conventional message (with protected branch detection) |
 | `/commit-push` | Commit and push in one operation |
 | `/commit-merge` | Commit and merge into target branch |
 | `/commit-sync` | Full sync: commit, push, and rebase on base branch |
@@ -79,7 +79,7 @@ chore/update-dependencies
 
 ### Safety Checks
 
-- Warns before commits to protected branches
+- **Protected branch detection**: Before committing, checks if you're on a protected branch (main, master, development, staging, production by default). Offers to create a feature branch automatically instead of committing directly to protected branches.
 - Confirms force push operations
 - Prevents accidental branch deletion
 

plugins/git-flow/commands/commit.md

@@ -6,13 +6,44 @@ Create a git commit with an auto-generated conventional commit message based on
 
 ## Behavior
 
-### Step 1: Analyze Changes
+### Step 1: Check for Protected Branch
+
+Before any commit operation, check if the current branch is protected:
+
+1. Get current branch: `git branch --show-current`
+2. Check against `GIT_PROTECTED_BRANCHES` (default: `main,master,development,staging,production`)
+
+If on a protected branch, warn the user:
+
+```
+⚠️  You are on a protected branch: development
+
+Protected branches typically have push restrictions that will prevent
+direct commits from being pushed to the remote.
+
+Options:
+1. Create a feature branch and continue (Recommended)
+2. Continue on this branch anyway (may fail on push)
+3. Cancel
+```
+
+**If option 1 (create feature branch):**
+- Prompt for branch type (feat/fix/chore/docs/refactor)
+- Prompt for brief description
+- Create branch using `/branch-start` naming conventions
+- Continue with commit on the new branch
+
+**If option 2 (continue anyway):**
+- Proceed with commit (user accepts risk of push rejection)
+- Display reminder: "Remember: push may be rejected by remote protection rules"
+
+### Step 2: Analyze Changes
 
 1. Run `git status` to see staged and unstaged changes
 2. Run `git diff --staged` to examine staged changes
 3. If nothing staged, prompt user to stage changes
 
-### Step 2: Generate Commit Message
+### Step 3: Generate Commit Message
 
 Analyze the changes and generate a conventional commit message:
 
@@ -38,7 +69,7 @@ Analyze the changes and generate a conventional commit message:
 
 **Scope:** Determined from changed files (e.g., `auth`, `api`, `ui`)
 
-### Step 3: Confirm or Edit
+### Step 4: Confirm or Edit
 
 Present the generated message:
 
@@ -58,7 +89,7 @@ Options:
 4. Cancel
 ```
 
-### Step 4: Execute Commit
+### Step 5: Execute Commit
 
 If confirmed, run:
 
@@ -75,6 +106,7 @@ EOF
 
 | Variable | Default | Description |
 |----------|---------|-------------|
+| `GIT_PROTECTED_BRANCHES` | `main,master,development,staging,production` | Branches that trigger protection warning |
 | `GIT_COMMIT_STYLE` | `conventional` | Message style (conventional, simple, detailed) |
 | `GIT_SIGN_COMMITS` | `false` | Use GPG signing |
 | `GIT_CO_AUTHOR` | `true` | Include Claude co-author footer |

plugins/pr-review/README.md

@@ -13,6 +13,9 @@ pr-review conducts comprehensive code reviews using specialized agents for secur
 | `/pr-review <pr#>` | Full multi-agent review |
 | `/pr-summary <pr#>` | Quick summary without full review |
 | `/pr-findings <pr#>` | Filter findings by category/confidence |
+| `/initial-setup` | Full interactive setup wizard |
+| `/project-init` | Quick project setup (system already configured) |
+| `/project-sync` | Sync configuration with current git remote |
 
 ## Review Agents
 

plugins/pr-review/hooks/hooks.json

@@ -2,8 +2,8 @@
   "hooks": {
     "SessionStart": [
       {
-        "type": "prompt",
-        "prompt": "[pr-review] Perform silent startup checks:\n\n1. Check if MCP venvs exist at the installed marketplace location. If the marketplace is installed but venvs are missing, warn the user: '[pr-review] MCP venvs missing - run setup.sh from installed marketplace location'.\n\n2. Check if the project git remote matches .env configuration (GITEA_ORG/GITEA_REPO). If mismatch, warn: '[pr-review] Git remote mismatch - run /project-sync'.\n\nStay silent if all checks pass or not applicable. Be quick and non-blocking."
+        "type": "command",
+        "command": "${CLAUDE_PLUGIN_ROOT}/hooks/startup-check.sh"
       }
     ]
   }

plugins/pr-review/hooks/startup-check.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+# pr-review startup check hook
+# Checks for common issues at session start
+# All output MUST have [pr-review] prefix
+
+PREFIX="[pr-review]"
+
+# Check if MCP venv exists
+PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "$(realpath "$0")")")}"
+VENV_PATH="$PLUGIN_ROOT/mcp-servers/gitea/.venv/bin/python"
+
+if [[ ! -f "$VENV_PATH" ]]; then
+    echo "$PREFIX MCP venvs missing - run setup.sh from installed marketplace"
+    exit 0
+fi
+
+# Check git remote vs .env config (only if .env exists)
+if [[ -f ".env" ]]; then
+    CONFIGURED_REPO=$(grep -E "^GITEA_REPO=" .env 2>/dev/null | cut -d'=' -f2 | tr -d '"' || true)
+    if [[ -n "$CONFIGURED_REPO" ]]; then
+        CURRENT_REMOTE=$(git remote get-url origin 2>/dev/null | sed 's/.*[:/]\([^/]*\/[^.]*\).*/\1/' || true)
+        if [[ -n "$CURRENT_REMOTE" && "$CONFIGURED_REPO" != "$CURRENT_REMOTE" ]]; then
+            echo "$PREFIX Git remote mismatch - run /pr-review:project-sync"
+            exit 0
+        fi
+    fi
+fi
+
+# All checks passed - say nothing
+exit 0

plugins/project-hygiene/README.md

@@ -20,7 +20,7 @@ claude plugin install project-hygiene
 
 ## How It Works
 
-The plugin registers a `task-completed` hook that runs after Claude completes any task. It:
+The plugin registers a `PostToolUse` hook (on Write and Edit tools) that runs after Claude modifies files. It:
 
 1. Scans for and deletes known temporary file patterns
 2. Removes temporary directories (`__pycache__`, `.pytest_cache`, etc.)

plugins/project-hygiene/hooks/cleanup.sh

@@ -1,365 +1,28 @@
 #!/bin/bash
 # project-hygiene cleanup hook
-# Runs after task completion to clean up temp files and manage orphans
+# Runs after file edits to clean up temp files
+# All output MUST have [project-hygiene] prefix
 
 set -euo pipefail
 
-# Configuration
+PREFIX="[project-hygiene]"
+
+# Read tool input from stdin (discard - we don't need it for cleanup)
+cat > /dev/null
+
 PROJECT_ROOT="${PROJECT_ROOT:-.}"
-PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "$(realpath "$0")")")}"
-CONFIG_FILE="${PROJECT_ROOT}/.hygiene.json"
-LOG_DIR="${PROJECT_ROOT}/.dev/logs"
-SCRATCH_DIR="${PROJECT_ROOT}/.dev/scratch"
-LOG_FILE="${LOG_DIR}/hygiene-$(date +%Y%m%d-%H%M%S).log"
-
-# Default allowed root files (can be overridden by .hygiene.json)
-DEFAULT_ALLOWED_ROOT=(
-    ".git"
-    ".gitignore"
-    ".gitattributes"
-    ".editorconfig"
-    ".env"
-    ".env.example"
-    ".env.local"
-    ".nvmrc"
-    ".node-version"
-    ".python-version"
-    ".ruby-version"
-    ".tool-versions"
-    "README.md"
-    "LICENSE"
-    "CHANGELOG.md"
-    "CONTRIBUTING.md"
-    "CLAUDE.md"
-    "package.json"
-    "package-lock.json"
-    "yarn.lock"
-    "pnpm-lock.yaml"
-    "Makefile"
-    "Dockerfile"
-    "docker-compose.yml"
-    "docker-compose.yaml"
-    "Cargo.toml"
-    "Cargo.lock"
-    "go.mod"
-    "go.sum"
-    "requirements.txt"
-    "setup.py"
-    "pyproject.toml"
-    "poetry.lock"
-    "Gemfile"
-    "Gemfile.lock"
-    "tsconfig.json"
-    "jsconfig.json"
-    ".eslintrc*"
-    ".prettierrc*"
-    "vite.config.*"
-    "webpack.config.*"
-    "rollup.config.*"
-    ".hygiene.json"
-)
-
-# Temp file patterns to delete
-TEMP_PATTERNS=(
-    "*.tmp"
-    "*.bak"
-    "*.swp"
-    "*.swo"
-    "*~"
-    ".DS_Store"
-    "Thumbs.db"
-    "*.log"
-    "*.orig"
-    "*.pyc"
-    "*.pyo"
-)
-
-# Directory patterns to delete
-TEMP_DIRS=(
-    "__pycache__"
-    ".pytest_cache"
-    ".mypy_cache"
-    ".ruff_cache"
-    "node_modules/.cache"
-    ".next/cache"
-    ".nuxt/.cache"
-    ".turbo"
-    "*.egg-info"
-    ".eggs"
-    "dist"
-    "build"
-)
-
-# Orphan patterns to identify
-ORPHAN_PATTERNS=(
-    "test_*.py"
-    "debug_*"
-    "*_backup.*"
-    "*_old.*"
-    "*_bak.*"
-    "*.backup"
-    "temp_*"
-    "tmp_*"
-)
-
-# Initialize
 DELETED_COUNT=0
-WARNED_COUNT=0
-ORPHAN_COUNT=0
-MOVE_ORPHANS=false
-
-# Logging function
-log() {
-    local msg="[$(date +%H:%M:%S)] $1"
-    echo "$msg"
-    if [[ -f "$LOG_FILE" ]]; then
-        echo "$msg" >> "$LOG_FILE"
-    fi
-}
-
-log_action() {
-    local action="$1"
-    local target="$2"
-    log "  $action: $target"
-}
-
-# Load project-local config if exists
-load_config() {
-    if [[ -f "$CONFIG_FILE" ]]; then
-        log "Loading config from $CONFIG_FILE"
-
-        # Check if move_orphans is enabled
-        if command -v jq &>/dev/null; then
-            MOVE_ORPHANS=$(jq -r '.move_orphans // false' "$CONFIG_FILE" 2>/dev/null || echo "false")
-
-            # Load additional allowed root files
-            local extra_allowed
-            extra_allowed=$(jq -r '.allowed_root_files // [] | .[]' "$CONFIG_FILE" 2>/dev/null || true)
-            if [[ -n "$extra_allowed" ]]; then
-                while IFS= read -r file; do
-                    DEFAULT_ALLOWED_ROOT+=("$file")
-                done <<< "$extra_allowed"
-            fi
-
-            # Load additional temp patterns
-            local extra_temp
-            extra_temp=$(jq -r '.temp_patterns // [] | .[]' "$CONFIG_FILE" 2>/dev/null || true)
-            if [[ -n "$extra_temp" ]]; then
-                while IFS= read -r pattern; do
-                    TEMP_PATTERNS+=("$pattern")
-                done <<< "$extra_temp"
-            fi
-
-            # Load ignore patterns (files to never touch)
-            IGNORE_PATTERNS=()
-            local ignore
-            ignore=$(jq -r '.ignore_patterns // [] | .[]' "$CONFIG_FILE" 2>/dev/null || true)
-            if [[ -n "$ignore" ]]; then
-                while IFS= read -r pattern; do
-                    IGNORE_PATTERNS+=("$pattern")
-                done <<< "$ignore"
-            fi
-        else
-            log "Warning: jq not installed, using default config"
-        fi
-    fi
-}
-
-# Check if file should be ignored
-should_ignore() {
-    local file="$1"
-    local basename
-    basename=$(basename "$file")
-
-    for pattern in "${IGNORE_PATTERNS[@]:-}"; do
-        if [[ "$basename" == $pattern ]] || [[ "$file" == $pattern ]]; then
-            return 0
-        fi
-    done
-    return 1
-}
-
-# Check if file is in allowed root list
-is_allowed_root() {
-    local file="$1"
-    local basename
-    basename=$(basename "$file")
-
-    for allowed in "${DEFAULT_ALLOWED_ROOT[@]}"; do
-        # Support wildcards in allowed patterns
-        if [[ "$basename" == $allowed ]]; then
-            return 0
-        fi
-    done
-    return 1
-}
-
-# Check if file matches orphan pattern
-is_orphan() {
-    local file="$1"
-    local basename
-    basename=$(basename "$file")
-
-    for pattern in "${ORPHAN_PATTERNS[@]}"; do
-        if [[ "$basename" == $pattern ]]; then
-            return 0
-        fi
-    done
-    return 1
-}
-
-# Setup directories
-setup_dirs() {
-    mkdir -p "$LOG_DIR"
-    if [[ "$MOVE_ORPHANS" == "true" ]]; then
-        mkdir -p "$SCRATCH_DIR"
-    fi
-
-    # Start log file
-    echo "=== Project Hygiene Cleanup ===" > "$LOG_FILE"
-    echo "Started: $(date)" >> "$LOG_FILE"
-    echo "Project: $PROJECT_ROOT" >> "$LOG_FILE"
-    echo "" >> "$LOG_FILE"
-}
-
-# Delete temp files
-cleanup_temp_files() {
-    log "Cleaning temp files..."
-
-    for pattern in "${TEMP_PATTERNS[@]}"; do
-        while IFS= read -r -d '' file; do
-            if should_ignore "$file"; then
-                continue
-            fi
-            rm -f "$file"
-            log_action "DELETED" "$file"
-            ((DELETED_COUNT++))
-        done < <(find "$PROJECT_ROOT" -name "$pattern" -type f -print0 2>/dev/null || true)
-    done
-}
-
-# Delete temp directories
-cleanup_temp_dirs() {
-    log "Cleaning temp directories..."
-
-    for pattern in "${TEMP_DIRS[@]}"; do
-        while IFS= read -r -d '' dir; do
-            if should_ignore "$dir"; then
-                continue
-            fi
-            rm -rf "$dir"
-            log_action "DELETED DIR" "$dir"
-            ((DELETED_COUNT++))
-        done < <(find "$PROJECT_ROOT" -name "$pattern" -type d -print0 2>/dev/null || true)
-    done
-}
-
-# Warn about unexpected root files
-check_root_files() {
-    log "Checking root files..."
-
-    local unexpected_files=()
 
+# Silently delete temp files
+for pattern in "*.tmp" "*.bak" "*.swp" "*~" ".DS_Store"; do
     while IFS= read -r -d '' file; do
-        local basename
-        basename=$(basename "$file")
+        rm -f "$file" 2>/dev/null && ((DELETED_COUNT++)) || true
+    done < <(find "$PROJECT_ROOT" -name "$pattern" -type f -print0 2>/dev/null || true)
+done
 
-        # Skip directories
-        [[ -d "$file" ]] && continue
+# Only output if we deleted something
+if [[ $DELETED_COUNT -gt 0 ]]; then
+    echo "$PREFIX Cleaned $DELETED_COUNT temp files"
+fi
 
-        # Skip if in allowed list
-        is_allowed_root "$basename" && continue
-
-        # Skip if should be ignored
-        should_ignore "$basename" && continue
-
-        unexpected_files+=("$basename")
-        log_action "WARNING" "Unexpected root file: $basename"
-        ((WARNED_COUNT++))
-    done < <(find "$PROJECT_ROOT" -maxdepth 1 -print0 2>/dev/null || true)
-
-    if [[ ${#unexpected_files[@]} -gt 0 ]]; then
-        log ""
-        log "⚠️  Unexpected files in project root:"
-        for f in "${unexpected_files[@]}"; do
-            log "    - $f"
-        done
-    fi
-}
-
-# Identify and handle orphaned files
-handle_orphans() {
-    log "Checking for orphaned files..."
-
-    local orphan_files=()
-
-    for pattern in "${ORPHAN_PATTERNS[@]}"; do
-        while IFS= read -r -d '' file; do
-            if should_ignore "$file"; then
-                continue
-            fi
-
-            orphan_files+=("$file")
-
-            if [[ "$MOVE_ORPHANS" == "true" ]]; then
-                local dest="${SCRATCH_DIR}/$(basename "$file")"
-                # Handle duplicates
-                if [[ -f "$dest" ]]; then
-                    dest="${SCRATCH_DIR}/$(date +%Y%m%d%H%M%S)_$(basename "$file")"
-                fi
-                mv "$file" "$dest"
-                log_action "MOVED" "$file -> $dest"
-            else
-                log_action "ORPHAN" "$file"
-            fi
-            ((ORPHAN_COUNT++))
-        done < <(find "$PROJECT_ROOT" -name "$pattern" -type f -print0 2>/dev/null || true)
-    done
-
-    if [[ ${#orphan_files[@]} -gt 0 && "$MOVE_ORPHANS" != "true" ]]; then
-        log ""
-        log "📦 Orphaned files found (enable move_orphans in .hygiene.json to auto-move):"
-        for f in "${orphan_files[@]}"; do
-            log "    - $f"
-        done
-    fi
-}
-
-# Summary
-print_summary() {
-    log ""
-    log "=== Cleanup Summary ==="
-    log "  Deleted: $DELETED_COUNT items"
-    log "  Warnings: $WARNED_COUNT unexpected root files"
-    log "  Orphans: $ORPHAN_COUNT files"
-    if [[ "$MOVE_ORPHANS" == "true" ]]; then
-        log "  Orphans moved to: $SCRATCH_DIR"
-    fi
-    log "  Log file: $LOG_FILE"
-    log ""
-}
-
-# Main
-main() {
-    cd "$PROJECT_ROOT" || exit 1
-
-    load_config
-    setup_dirs
-
-    log "Starting project hygiene cleanup..."
-    log ""
-
-    cleanup_temp_files
-    cleanup_temp_dirs
-    check_root_files
-    handle_orphans
-
-    print_summary
-
-    # Exit with warning code if issues found
-    if [[ $WARNED_COUNT -gt 0 || $ORPHAN_COUNT -gt 0 ]]; then
-        exit 0  # Still success, but logged warnings
-    fi
-}
-
-main "$@"
+exit 0

plugins/projman/README.md

@@ -13,7 +13,7 @@ Projman transforms a proven 15-sprint workflow into a distributable Claude Code
 - **Milestones** - Sprint milestone management and tracking
 - **Lessons Learned** - Systematic capture and search via Gitea Wiki
 - **Branch-Aware Security** - Prevents accidental changes on production branches
-- **Three-Agent Model** - Planner, Orchestrator, and Executor agents
+- **Four-Agent Model** - Planner, Orchestrator, Executor, and Code Reviewer agents
 - **CLI Tools Blocked** - All operations via MCP tools only (no `tea` or `gh`)
 
 ## Quick Start
@@ -461,20 +461,8 @@ projman/
 ├── .claude-plugin/
 │   └── plugin.json          # Plugin manifest
 ├── .mcp.json                # MCP server configuration
-├── mcp-servers/             # Bundled MCP server
-│   └── gitea/
-│       ├── .venv/
-│       ├── requirements.txt
-│       ├── mcp_server/
-│       │   ├── server.py
-│       │   ├── gitea_client.py
-│       │   └── tools/
-│       │       ├── issues.py
-│       │       ├── labels.py
-│       │       ├── wiki.py
-│       │       ├── milestones.py
-│       │       └── dependencies.py
-│       └── tests/
+├── mcp-servers/
+│   └── gitea -> ../../../mcp-servers/gitea  # SYMLINK to shared MCP server
 ├── commands/                # Slash commands
 │   ├── sprint-plan.md
 │   ├── sprint-start.md

plugins/projman/commands/debug-report.md

@@ -4,7 +4,7 @@ description: Run diagnostics and create structured issue in marketplace reposito
 
 # Debug Report
 
-Run diagnostic checks on projman MCP tools and create a structured issue in the marketplace repository for investigation.
+Create structured issues in the marketplace repository - either from automated diagnostic tests OR from user-reported problems.
 
 ## Prerequisites
 
@@ -20,6 +20,101 @@ If not configured, ask the user for the marketplace repository path.
 
 You MUST follow these steps in order. Do NOT skip any step.
 
+### Step 0: Select Report Mode
+
+Use AskUserQuestion to determine what the user wants to report:
+
+```
+What would you like to report?
+
+[ ] Run automated diagnostics - Test MCP tools and report failures
+[ ] Report an issue I experienced - Describe a problem with any plugin command
+```
+
+Store the selection as `REPORT_MODE`:
+- "automated" → Continue to Step 1
+- "user-reported" → Skip to Step 0.1
+
+---
+
+### Step 0.1: Gather User Feedback (User-Reported Mode Only)
+
+If `REPORT_MODE` is "user-reported", gather structured feedback.
+
+**Question 1: What were you trying to do?**
+
+Use AskUserQuestion:
+```
+Which plugin/command were you using?
+
+[ ] projman (sprint planning, issues, labels)
+[ ] git-flow (commits, branches)
+[ ] pr-review (pull request review)
+[ ] cmdb-assistant (NetBox integration)
+[ ] doc-guardian (documentation)
+[ ] code-sentinel (security, refactoring)
+[ ] Other - I'll describe it
+```
+
+Store as `AFFECTED_PLUGIN`.
+
+Then ask for the specific command (free text):
+```
+What command or tool were you using? (e.g., /sprint-plan, virt_update_vm)
+```
+
+Store as `AFFECTED_COMMAND`.
+
+**Question 2: What was your goal?**
+
+```
+Briefly describe what you were trying to accomplish:
+```
+
+Store as `USER_GOAL`.
+
+**Question 3: What went wrong?**
+
+Use AskUserQuestion:
+```
+What type of problem did you encounter?
+
+[ ] Error message - Command failed with an error
+[ ] Missing feature - Tool doesn't support what I need
+[ ] Unexpected behavior - It worked but did the wrong thing
+[ ] Documentation issue - Instructions were unclear or wrong
+[ ] Other - I'll describe it
+```
+
+Store as `PROBLEM_TYPE`.
+
+Then ask for details (free text):
+```
+Describe what happened. Include any error messages if applicable:
+```
+
+Store as `PROBLEM_DESCRIPTION`.
+
+**Question 4: Expected vs Actual**
+
+```
+What did you expect to happen?
+```
+
+Store as `EXPECTED_BEHAVIOR`.
+
+**Question 5: Workaround (optional)**
+
+```
+Did you find a workaround? If so, describe it (or skip):
+```
+
+Store as `WORKAROUND` (may be empty).
+
+After gathering feedback, continue to Step 1 for context gathering, then skip to Step 5.1.
+
+---
+
 ### Step 1: Gather Project Context
 
 Run these Bash commands to capture project information:
@@ -43,6 +138,46 @@ Store all values:
 - `CURRENT_BRANCH`: Current branch name
 - `WORKING_DIR`: Current working directory
 
+### Step 1.5: Detect Sprint Context
+
+Determine if this debug issue should be associated with an active sprint.
+
+**1. Check for active sprint milestone:**
+
+```
+mcp__plugin_projman_gitea__list_milestones(repo=PROJECT_REPO, state="open")
+```
+
+Store the first open milestone as `ACTIVE_SPRINT` (if any).
+
+**2. Analyze branch context:**
+
+| Branch Pattern | Context |
+|----------------|---------|
+| `feat/*`, `fix/*`, `issue-*` | Sprint work - likely related to current sprint |
+| `main`, `master`, `development` | Production/standalone - not sprint-related |
+| Other | Unknown - ask user |
+
+**3. Determine sprint association:**
+
+```
+IF ACTIVE_SPRINT exists AND CURRENT_BRANCH matches sprint pattern (feat/*, fix/*, issue-*):
+  → SPRINT_CONTEXT = "detected"
+  → Ask user: "Active sprint detected: [SPRINT_NAME]. Is this bug related to sprint work?"
+    Options:
+    - Yes, add to sprint (will associate with milestone)
+    - No, standalone fix (no milestone)
+  → Store choice as ASSOCIATE_WITH_SPRINT (true/false)
+
+ELSE IF ACTIVE_SPRINT exists AND CURRENT_BRANCH is main/development:
+  → SPRINT_CONTEXT = "production"
+  → ASSOCIATE_WITH_SPRINT = false (standalone fix, no question needed)
+
+ELSE:
+  → SPRINT_CONTEXT = "none"
+  → ASSOCIATE_WITH_SPRINT = false
+```
+
 ### Step 2: Read Marketplace Configuration
 
 ```bash
@@ -51,7 +186,9 @@ grep PROJMAN_MARKETPLACE_REPO .env
 
 Store as `MARKETPLACE_REPO`. If not found, ask the user.
 
-### Step 3: Run Diagnostic Suite
+### Step 3: Run Diagnostic Suite (Automated Mode Only)
+
+**Skip this step if `REPORT_MODE` is "user-reported"** → Go to Step 5.1
 
 Run each MCP tool with explicit `repo` parameter. Record success/failure and full response.
 
@@ -91,7 +228,9 @@ For each test, record:
 - Status: PASS or FAIL
 - Response or error message
 
-### Step 4: Analyze Results
+### Step 4: Analyze Results (Automated Mode Only)
+
+**Skip this step if `REPORT_MODE` is "user-reported"** → Go to Step 5.1
 
 Count failures and categorize errors:
 
@@ -105,7 +244,90 @@ Count failures and categorize errors:
 
 For each failure, write a hypothesis about the likely cause.
 
-### Step 5: Generate Issue Content
+### Step 5: Generate Smart Labels (Automated Mode Only)
+
+**Skip this step if `REPORT_MODE` is "user-reported"** → Go to Step 5.1
+
+Generate appropriate labels based on the diagnostic results.
+
+**1. Build context string for label suggestion:**
+
+```
+LABEL_CONTEXT = "Bug fix: " + [summary of main failure] + ". " +
+                "Failed tools: " + [list of failed tool names] + ". " +
+                "Error category: " + [detected error category from Step 4]
+```
+
+**2. Get suggested labels:**
+
+```
+mcp__plugin_projman_gitea__suggest_labels(
+  repo=PROJECT_REPO,
+  context=LABEL_CONTEXT
+)
+```
+
+**3. Merge with base labels:**
+
+```
+BASE_LABELS = ["Type: Bug", "Source: Diagnostic", "Agent: Claude"]
+SUGGESTED_LABELS = [result from suggest_labels]
+
+# Combine, avoiding duplicates
+FINAL_LABELS = BASE_LABELS + [label for label in SUGGESTED_LABELS if label not in BASE_LABELS]
+```
+
+The final label set should include:
+- **Always**: `Type: Bug`, `Source: Diagnostic`, `Agent: Claude`
+- **If detected**: `Component: *`, `Complexity: *`, `Risk: *`, `Priority: *`
+
+After generating labels, continue to Step 6.
+
+---
+
+### Step 5.1: Generate Labels (User-Reported Mode Only)
+
+**Only execute this step if `REPORT_MODE` is "user-reported"**
+
+**1. Map problem type to labels:**
+
+| PROBLEM_TYPE | Labels |
+|--------------|--------|
+| Error message | `Type: Bug` |
+| Missing feature | `Type: Enhancement` |
+| Unexpected behavior | `Type: Bug` |
+| Documentation issue | `Type: Documentation` |
+| Other | `Type: Bug` (default) |
+
+**2. Map plugin to component:**
+
+| AFFECTED_PLUGIN | Component Label |
+|-----------------|-----------------|
+| projman | `Component: Commands` |
+| git-flow | `Component: Commands` |
+| pr-review | `Component: Commands` |
+| cmdb-assistant | `Component: API` |
+| doc-guardian | `Component: Commands` |
+| code-sentinel | `Component: Commands` |
+| Other | *(no component label)* |
+
+**3. Build final labels:**
+
+```
+BASE_LABELS = ["Source: User-Reported", "Agent: Claude"]
+TYPE_LABEL = [mapped from PROBLEM_TYPE]
+COMPONENT_LABEL = [mapped from AFFECTED_PLUGIN, if any]
+
+FINAL_LABELS = BASE_LABELS + TYPE_LABEL + COMPONENT_LABEL
+```
+
+After generating labels, continue to Step 6.1.
+
+---
+
+### Step 6: Generate Issue Content (Automated Mode Only)
+
+**Skip this step if `REPORT_MODE` is "user-reported"** → Go to Step 6.1
 
 Use this exact template:
 
@@ -179,85 +401,182 @@ Use this exact template:
 
 ---
 
-*Generated by /debug-report - Labels: Type: Bug, Source: Diagnostic, Agent: Claude*
+*Generated by /debug-report (automated) - Labels: Type: Bug, Source: Diagnostic, Agent: Claude*
 ```
 
-### Step 6: Create Issue in Marketplace
+After generating content, continue to Step 7.
 
-**First, check if MCP tools are available.** Attempt to use an MCP tool. If you receive "tool not found", "not in function list", or similar error, the MCP server is not accessible in this session - use the curl fallback.
+---
 
-#### Option A: MCP Available (preferred)
+### Step 6.1: Generate Issue Content (User-Reported Mode Only)
 
-```
-mcp__plugin_projman_gitea__create_issue(
-  repo=MARKETPLACE_REPO,
-  title="[Diagnostic] [summary of main failure]",
-  body=[generated content from Step 5],
-  labels=["Type: Bug", "Source: Diagnostic", "Agent: Claude"]
-)
+**Only execute this step if `REPORT_MODE` is "user-reported"**
+
+Use this template for user-reported issues:
+
+```markdown
+## User-Reported Issue
+
+**Reported**: [ISO timestamp]
+**Reporter**: Claude Code via /debug-report (user feedback)
+
+## Context
+
+| Field | Value |
+|-------|-------|
+| Plugin | `[AFFECTED_PLUGIN]` |
+| Command/Tool | `[AFFECTED_COMMAND]` |
+| Repository | `[PROJECT_REPO]` |
+| Working Directory | `[WORKING_DIR]` |
+| Branch | `[CURRENT_BRANCH]` |
+
+## Problem Description
+
+### Goal
+[USER_GOAL]
+
+### What Happened
+**Problem Type**: [PROBLEM_TYPE]
+
+[PROBLEM_DESCRIPTION]
+
+### Expected Behavior
+[EXPECTED_BEHAVIOR]
+
+## Workaround
+[WORKAROUND if provided, otherwise "None identified"]
+
+## Investigation Hints
+
+Based on the affected plugin/command, relevant files to check:
+
+[Generate based on AFFECTED_PLUGIN:]
+
+**projman:**
+- `plugins/projman/commands/[AFFECTED_COMMAND].md`
+- `mcp-servers/gitea/mcp_server/tools/*.py`
+
+**git-flow:**
+- `plugins/git-flow/commands/[AFFECTED_COMMAND].md`
+
+**pr-review:**
+- `plugins/pr-review/commands/[AFFECTED_COMMAND].md`
+- `mcp-servers/gitea/mcp_server/tools/pull_requests.py`
+
+**cmdb-assistant:**
+- `plugins/cmdb-assistant/commands/[AFFECTED_COMMAND].md`
+- `mcp-servers/netbox/mcp_server/tools/*.py`
+- `mcp-servers/netbox/mcp_server/server.py` (tool schemas)
+
+**doc-guardian / code-sentinel:**
+- `plugins/[plugin]/commands/[AFFECTED_COMMAND].md`
+- `plugins/[plugin]/hooks/*.md`
+
+---
+
+*Generated by /debug-report (user feedback) - Labels: [FINAL_LABELS]*
 ```
 
-If labels don't exist, create issue without labels.
+After generating content, continue to Step 7.
 
-#### Option B: MCP Unavailable - Use curl Fallback
+---
 
-If MCP tools are not available (the very issue you may be diagnosing), use this fallback:
+### Step 7: Create Issue in Marketplace
 
-**1. Check for Gitea credentials:**
+**IMPORTANT:** Always use curl to create issues in the marketplace repo. This avoids branch protection restrictions and MCP context issues that can block issue creation when working on protected branches.
+
+**1. Load Gitea credentials:**
 
 ```bash
 if [[ -f ~/.config/claude/gitea.env ]]; then
   source ~/.config/claude/gitea.env
-  echo "Credentials found. API URL: $GITEA_API_URL"
+  echo "Credentials loaded. API URL: $GITEA_API_URL"
 else
-  echo "No credentials at ~/.config/claude/gitea.env"
+  echo "ERROR: No credentials at ~/.config/claude/gitea.env"
 fi
 ```
 
-**2. If credentials exist, create issue via curl with proper JSON escaping:**
+**2. Fetch label IDs from marketplace repo:**
 
-Create secure temp files and save content:
+Labels depend on `REPORT_MODE`:
+
+**Automated mode:**
+- `Source/Diagnostic` (always)
+- `Type/Bug` (always)
+
+**User-reported mode:**
+- `Source/User-Reported` (always)
+- Type label from Step 5.1 (Bug, Enhancement, or Documentation)
+- Component label from Step 5.1 (if applicable)
+
+```bash
+# Fetch all labels from marketplace repo
+LABELS_JSON=$(curl -s "${GITEA_API_URL}/repos/${MARKETPLACE_REPO}/labels" \
+  -H "Authorization: token ${GITEA_API_TOKEN}")
+
+# Extract label IDs based on FINAL_LABELS from Step 5 or 5.1
+# Build LABEL_IDS array with IDs of labels that exist in the repo
+# Example for automated mode:
+SOURCE_ID=$(echo "$LABELS_JSON" | jq -r '.[] | select(.name == "Source/Diagnostic") | .id')
+TYPE_ID=$(echo "$LABELS_JSON" | jq -r '.[] | select(.name == "Type/Bug") | .id')
+
+# Example for user-reported mode (adjust based on FINAL_LABELS):
+# SOURCE_ID=$(echo "$LABELS_JSON" | jq -r '.[] | select(.name == "Source/User-Reported") | .id')
+# TYPE_ID=$(echo "$LABELS_JSON" | jq -r '.[] | select(.name == "[TYPE_LABEL]") | .id')
+
+# Build label array from found IDs
+LABEL_IDS="[$(echo "$SOURCE_ID,$TYPE_ID" | sed 's/,,*/,/g; s/^,//; s/,$//')]"
+echo "Label IDs to apply: $LABEL_IDS"
+```
+
+**3. Create issue with labels via curl:**
+
+**Title format depends on `REPORT_MODE`:**
+- Automated: `[Diagnostic] [summary of main failure]`
+- User-reported: `[AFFECTED_PLUGIN] [brief summary of PROBLEM_DESCRIPTION]`
 
 ```bash
 # Create temp files with restrictive permissions
-DIAG_TITLE=$(mktemp -p /tmp -m 600 diag-title.XXXXXX)
-DIAG_BODY=$(mktemp -p /tmp -m 600 diag-body.XXXXXX)
-DIAG_PAYLOAD=$(mktemp -p /tmp -m 600 diag-payload.XXXXXX)
+DIAG_TITLE=$(mktemp -t diag-title.XXXXXX)
+DIAG_BODY=$(mktemp -t diag-body.XXXXXX)
+DIAG_PAYLOAD=$(mktemp -t diag-payload.XXXXXX)
 
-# Save title
-echo "[Diagnostic] [summary of main failure]" > "$DIAG_TITLE"
+# Save title (format depends on REPORT_MODE)
+# Automated: "[Diagnostic] [summary of main failure]"
+# User-reported: "[AFFECTED_PLUGIN] [brief summary]"
+echo "[Title based on REPORT_MODE]" > "$DIAG_TITLE"
 
-# Save body (paste Step 5 content) - heredoc delimiter prevents shell expansion
+# Save body (paste Step 6 or 6.1 content) - heredoc delimiter prevents shell expansion
 cat > "$DIAG_BODY" << 'DIAGNOSTIC_EOF'
-[Paste the full issue content from Step 5 here]
+[Paste the full issue content from Step 6 or 6.1 here]
 DIAGNOSTIC_EOF
-```
 
-Construct JSON safely using jq's --rawfile (avoids command substitution):
-
-```bash
-# Build JSON payload using jq with --rawfile for safe content handling
+# Build JSON payload with labels using jq
 jq -n \
   --rawfile title "$DIAG_TITLE" \
   --rawfile body "$DIAG_BODY" \
-  '{title: ($title | rtrimstr("\n")), body: $body}' > "$DIAG_PAYLOAD"
+  --argjson labels "$LABEL_IDS" \
+  '{title: ($title | rtrimstr("\n")), body: $body, labels: $labels}' > "$DIAG_PAYLOAD"
 
 # Create issue using the JSON file
-curl -s -X POST "${GITEA_API_URL}/repos/${MARKETPLACE_REPO}/issues" \
+RESULT=$(curl -s -X POST "${GITEA_API_URL}/repos/${MARKETPLACE_REPO}/issues" \
   -H "Authorization: token ${GITEA_API_TOKEN}" \
   -H "Content-Type: application/json" \
-  -d @"$DIAG_PAYLOAD" | jq '.html_url // .'
+  -d @"$DIAG_PAYLOAD")
+
+# Extract and display the issue URL
+echo "$RESULT" | jq -r '.html_url // "Error: " + (.message // "Unknown error")'
 
 # Secure cleanup
 rm -f "$DIAG_TITLE" "$DIAG_BODY" "$DIAG_PAYLOAD"
 ```
 
-**3. If no credentials found, save report locally:**
+**4. If no credentials found, save report locally:**
 
 ```bash
-REPORT_FILE=$(mktemp -p /tmp -m 600 diagnostic-report-XXXXXX.md)
+REPORT_FILE=$(mktemp -t diagnostic-report-XXXXXX.md)
 cat > "$REPORT_FILE" << 'DIAGNOSTIC_EOF'
-[Paste the full issue content from Step 5 here]
+[Paste the full issue content from Step 6 here]
 DIAGNOSTIC_EOF
 echo "Report saved to: $REPORT_FILE"
 ```
@@ -265,7 +584,7 @@ echo "Report saved to: $REPORT_FILE"
 Then inform the user:
 
 ```
-MCP tools are unavailable and no Gitea credentials found at ~/.config/claude/gitea.env.
+No Gitea credentials found at ~/.config/claude/gitea.env.
 
 Diagnostic report saved to: [REPORT_FILE]
 
@@ -274,10 +593,11 @@ To create the issue manually:
 2. Or create issue directly at: http://gitea.hotserv.cloud/[MARKETPLACE_REPO]/issues/new
 ```
 
-### Step 7: Report to User
+### Step 8: Report to User
 
-Display summary:
+Display summary based on `REPORT_MODE`:
 
+**Automated Mode:**
 ```
 Debug Report Complete
 =====================
@@ -299,17 +619,38 @@ Next Steps:
   3. Select issue #[N] to investigate
 ```
 
+**User-Reported Mode:**
+```
+Issue Report Complete
+=====================
+
+Plugin: [AFFECTED_PLUGIN]
+Command: [AFFECTED_COMMAND]
+Problem: [PROBLEM_TYPE]
+
+Issue Created: [issue URL]
+
+Your feedback has been captured. The development team will
+investigate and may follow up with questions.
+
+Next Steps:
+  1. Switch to marketplace repo: cd [marketplace path]
+  2. Run: /debug-review
+  3. Select issue #[N] to investigate
+```
+
 ## DO NOT
 
 - **DO NOT** attempt to fix anything - only report
-- **DO NOT** create issues if all tests pass (just report success)
-- **DO NOT** skip any diagnostic test
+- **DO NOT** create issues if all automated tests pass (unless in user-reported mode)
+- **DO NOT** skip any diagnostic test in automated mode
 - **DO NOT** call MCP tools without the `repo` parameter
-- **DO NOT** ask user questions during execution - run autonomously
+- **DO NOT** skip user questions in user-reported mode - gather complete feedback
+- **DO NOT** use MCP tools to create issues in the marketplace - always use curl (avoids branch restrictions)
 
-## If All Tests Pass
+## If All Tests Pass (Automated Mode Only)
 
-If all 5 tests pass, report success without creating an issue:
+If all 5 tests pass in automated mode, report success without creating an issue:
 
 ```
 Debug Report Complete
@@ -322,8 +663,8 @@ Failed: 0
 
 All diagnostics passed. No issues to report.
 
-If you're experiencing a specific problem, please describe it
-and I can create a manual bug report.
+If you're experiencing a specific problem, run /debug-report again
+and select "Report an issue I experienced" to describe it.
 ```
 
 ## Troubleshooting
@@ -336,7 +677,12 @@ and I can create a manual bug report.
 - Check if in a git repository: `git rev-parse --git-dir`
 - If not a git repo, ask user for the repository path
 
-**MCP tools not available**
-- Use the curl fallback in Step 6, Option B
-- Requires Gitea credentials at `~/.config/claude/gitea.env`
-- If no credentials, report will be saved locally for manual submission
+**Gitea credentials not found**
+- Credentials must be at `~/.config/claude/gitea.env`
+- If missing, the report will be saved locally for manual submission
+- See docs/CONFIGURATION.md for setup instructions
+
+**Labels not applied to issue**
+- Verify labels exist in the marketplace repo: `Source/Diagnostic`, `Type/Bug`
+- Check the label fetch output in Step 7.2 for errors
+- If labels don't exist, create them first with `/labels-sync` in the marketplace repo

plugins/projman/commands/debug-review.md

@@ -195,6 +195,74 @@ Does this analysis match your understanding of the problem?
 
 Do NOT proceed until user approves.
 
+### Step 9.5: Search Lessons Learned
+
+Before proposing a fix, search for relevant lessons from past fixes.
+
+**1. Extract search tags from the issue:**
+
+```
+SEARCH_TAGS = []
+# Add tool names
+for each failed_tool in issue:
+  SEARCH_TAGS.append(tool_name)  # e.g., "get_labels", "validate_repo_org"
+
+# Add error category
+SEARCH_TAGS.append(error_category)  # e.g., "parameter-format", "authentication"
+
+# Add component if identifiable
+if error relates to MCP server:
+  SEARCH_TAGS.append("mcp")
+if error relates to command:
+  SEARCH_TAGS.append("command")
+```
+
+**2. Search lessons learned:**
+
+```
+mcp__plugin_projman_gitea__search_lessons(
+  repo=REPO_NAME,
+  tags=SEARCH_TAGS,
+  limit=5
+)
+```
+
+**3. Also search by error keywords:**
+
+```
+mcp__plugin_projman_gitea__search_lessons(
+  repo=REPO_NAME,
+  query=[key error message words],
+  limit=5
+)
+```
+
+**4. Display relevant lessons (if any):**
+
+```
+Related Lessons Learned
+=======================
+
+Found [N] relevant lessons from past fixes:
+
+📚 Lesson: "Sprint 14 - Parameter validation in MCP tools"
+   Tags: mcp, get_labels, parameter-format
+   Summary: Always validate repo parameter format before API calls
+   Prevention: Add format check at function entry
+
+📚 Lesson: "Sprint 12 - Graceful fallback for missing config"
+   Tags: configuration, fallback
+   Summary: Commands should work even without .env
+   Prevention: Check for env vars, use sensible defaults
+
+These lessons may inform your fix approach.
+```
+
+If no lessons found, display:
+```
+No related lessons found. This may be a new type of issue.
+```
+
 ### Step 10: Propose Fix Approach
 
 Based on the analysis, propose a specific fix:
@@ -342,7 +410,118 @@ Next Steps:
   1. Review and merge PR #81
   2. In test project, pull latest plugin version
   3. Run /debug-report to verify fix
-  4. If passing, close issue #80
+  4. Come back and run Step 15 to close issue and capture lesson
+```
+
+### Step 15: Verify, Close, and Capture Lesson
+
+**This step runs AFTER the user has verified the fix works.**
+
+When user returns and confirms the fix is working:
+
+**1. Close the issue:**
+
+```
+mcp__plugin_projman_gitea__update_issue(
+  repo=REPO_NAME,
+  issue_number=ISSUE_NUMBER,
+  state="closed"
+)
+```
+
+**2. Ask about lesson capture:**
+
+Use AskUserQuestion:
+
+```
+This fix addressed [ERROR_TYPE] in [COMPONENT].
+
+Would you like to capture this as a lesson learned?
+
+Options:
+- Yes, capture lesson (helps avoid similar issues in future)
+- No, skip (trivial fix or already documented)
+```
+
+**3. If user chooses Yes, auto-generate lesson content:**
+
+```
+LESSON_TITLE = "Sprint [N] - [Brief description of fix]"
+  # Example: "Sprint 17 - MCP parameter validation"
+
+LESSON_CONTENT = """
+## Context
+
+[What was happening when the issue occurred]
+- Command/tool being used: [FAILED_TOOL]
+- Error encountered: [ERROR_MESSAGE]
+
+## Problem
+
+[Root cause identified during investigation]
+
+## Solution
+
+[What was changed to fix it]
+- Files modified: [LIST]
+- PR: #[PR_NUMBER]
+
+## Prevention
+
+[How to avoid this in the future]
+
+## Related
+
+- Issue: #[ISSUE_NUMBER]
+- PR: #[PR_NUMBER]
+"""
+
+LESSON_TAGS = [
+  tool_name,        # e.g., "get_labels"
+  error_category,   # e.g., "parameter-format"
+  component,        # e.g., "mcp", "command"
+  "bug-fix"
+]
+```
+
+**4. Show lesson preview and ask for approval:**
+
+```
+Lesson Preview
+==============
+
+Title: [LESSON_TITLE]
+Tags: [LESSON_TAGS]
+
+Content:
+[LESSON_CONTENT]
+
+Save this lesson? (Y/N/Edit)
+```
+
+**5. If approved, create the lesson:**
+
+```
+mcp__plugin_projman_gitea__create_lesson(
+  repo=REPO_NAME,
+  title=LESSON_TITLE,
+  content=LESSON_CONTENT,
+  tags=LESSON_TAGS,
+  category="sprints"
+)
+```
+
+**6. Report completion:**
+
+```
+Issue Closed & Lesson Captured
+==============================
+
+Issue #[N]: CLOSED
+Lesson: "[LESSON_TITLE]" saved to wiki
+
+This lesson will be surfaced in future /debug-review
+sessions when similar errors are encountered.
 ```
 
 ## DO NOT
@@ -350,8 +529,9 @@ Next Steps:
 - **DO NOT** skip reading relevant files - this is MANDATORY
 - **DO NOT** proceed past approval gates without user confirmation
 - **DO NOT** guess at fixes without evidence from code
-- **DO NOT** close issues - let user verify fix works first
+- **DO NOT** close issues until user confirms fix works (Step 15)
 - **DO NOT** commit directly to development or main branches
+- **DO NOT** skip the lessons learned search - past fixes inform better solutions
 
 ## If Investigation Finds No Bug
 

plugins/projman/commands/labels-sync.md

@@ -62,12 +62,20 @@ Verify these required label categories exist:
 
 ### Step 6: Create Missing Labels (if any)
 
-For each missing required label, call:
+Use `create_label_smart` which automatically creates labels at the correct level:
+- **Organization level**: Type/*, Priority/*, Complexity/*, Effort/*, Risk/*, Source/*, Agent/*
+- **Repository level**: Component/*, Tech/*
 
 ```
-mcp__plugin_projman_gitea__create_label(repo=REPO_NAME, name="Type: Bug", color="d73a4a")
+mcp__plugin_projman_gitea__create_label_smart(repo=REPO_NAME, name="Type/Bug", color="d73a4a")
 ```
 
+This automatically detects whether to create at org or repo level based on the category.
+
+**Alternative (explicit control):**
+- Org labels: `create_org_label(org="org-name", name="Type/Bug", color="d73a4a")`
+- Repo labels: `create_label(repo=REPO_NAME, name="Component/Backend", color="5319e7")`
+
 Use the label format that matches existing labels in the repo (slash `/` or colon-space `: `).
 
 ### Step 7: Report Results

plugins/projman/hooks/hooks.json

@@ -2,8 +2,8 @@
   "hooks": {
     "SessionStart": [
       {
-        "type": "prompt",
-        "prompt": "[projman] Perform silent startup checks:\n\n1. Check if MCP venvs exist at the installed marketplace location. If the marketplace is installed but venvs are missing, warn the user: '[projman] MCP venvs missing - run setup.sh from installed marketplace location'.\n\n2. Check if the project git remote matches .env configuration (GITEA_ORG/GITEA_REPO). If mismatch, warn: '[projman] Git remote mismatch - run /project-sync'.\n\nStay silent if all checks pass or not applicable. Be quick and non-blocking."
+        "type": "command",
+        "command": "${CLAUDE_PLUGIN_ROOT}/hooks/startup-check.sh"
       }
     ]
   }

plugins/projman/hooks/startup-check.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+# projman startup check hook
+# Checks for common issues at session start
+# All output MUST have [projman] prefix
+
+PREFIX="[projman]"
+
+# Check if MCP venv exists
+PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(dirname "$(dirname "$(realpath "$0")")")}"
+VENV_PATH="$PLUGIN_ROOT/mcp-servers/gitea/.venv/bin/python"
+
+if [[ ! -f "$VENV_PATH" ]]; then
+    echo "$PREFIX MCP venvs missing - run setup.sh from installed marketplace"
+    exit 0
+fi
+
+# Check git remote vs .env config (only if .env exists)
+if [[ -f ".env" ]]; then
+    CONFIGURED_REPO=$(grep -E "^GITEA_REPO=" .env 2>/dev/null | cut -d'=' -f2 | tr -d '"' || true)
+    if [[ -n "$CONFIGURED_REPO" ]]; then
+        CURRENT_REMOTE=$(git remote get-url origin 2>/dev/null | sed 's/.*[:/]\([^/]*\/[^.]*\).*/\1/' || true)
+        if [[ -n "$CURRENT_REMOTE" && "$CONFIGURED_REPO" != "$CURRENT_REMOTE" ]]; then
+            echo "$PREFIX Git remote mismatch - run /project-sync"
+            exit 0
+        fi
+    fi
+fi
+
+# All checks passed - say nothing
+exit 0

scripts/post-update.sh

@@ -67,6 +67,7 @@ main() {
     # Shared MCP servers at repository root (v3.0.0+)
     update_mcp_server "gitea"
     update_mcp_server "netbox"
+    update_mcp_server "data-platform"
 
     check_changelog
 
@@ -78,3 +79,8 @@ main() {
 }
 
 main "$@"
+
+# Clear plugin cache to ensure fresh hooks are loaded
+echo "Clearing plugin cache..."
+rm -rf ~/.claude/plugins/cache/leo-claude-mktplace/
+echo "Cache cleared"

scripts/release.sh

@@ -0,0 +1,172 @@
+#!/bin/bash
+# release.sh - Create a new release with version consistency
+#
+# Usage: ./scripts/release.sh X.Y.Z
+#
+# This script ensures all version references are updated consistently:
+# 1. CHANGELOG.md - [Unreleased] becomes [X.Y.Z] - YYYY-MM-DD
+# 2. README.md - Title updated to vX.Y.Z
+# 3. marketplace.json - version field updated
+# 4. Git commit and tag created
+#
+# Prerequisites:
+# - Clean working directory (no uncommitted changes)
+# - [Unreleased] section in CHANGELOG.md with content
+# - On development branch
+
+set -e
+
+VERSION=$1
+DATE=$(date +%Y-%m-%d)
+
+# Colors for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+error() { echo -e "${RED}ERROR: $1${NC}" >&2; exit 1; }
+warn() { echo -e "${YELLOW}WARNING: $1${NC}"; }
+success() { echo -e "${GREEN}$1${NC}"; }
+info() { echo -e "$1"; }
+
+# Validate arguments
+if [ -z "$VERSION" ]; then
+    echo "Usage: ./scripts/release.sh X.Y.Z"
+    echo ""
+    echo "Example: ./scripts/release.sh 3.2.0"
+    echo ""
+    echo "This will:"
+    echo "  1. Update CHANGELOG.md [Unreleased] -> [X.Y.Z] - $(date +%Y-%m-%d)"
+    echo "  2. Update README.md title to vX.Y.Z"
+    echo "  3. Update marketplace.json version to X.Y.Z"
+    echo "  4. Commit with message 'chore: release vX.Y.Z'"
+    echo "  5. Create git tag vX.Y.Z"
+    exit 1
+fi
+
+# Validate version format
+if ! [[ "$VERSION" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+    error "Invalid version format. Use X.Y.Z (e.g., 3.2.0)"
+fi
+
+# Check we're in the right directory
+if [ ! -f "CHANGELOG.md" ] || [ ! -f "README.md" ] || [ ! -f ".claude-plugin/marketplace.json" ]; then
+    error "Must run from repository root (CHANGELOG.md, README.md, .claude-plugin/marketplace.json must exist)"
+fi
+
+# Check for clean working directory
+if [ -n "$(git status --porcelain)" ]; then
+    warn "Working directory has uncommitted changes"
+    echo ""
+    git status --short
+    echo ""
+    read -p "Continue anyway? [y/N] " -n 1 -r
+    echo
+    if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+        exit 1
+    fi
+fi
+
+# Check current branch
+BRANCH=$(git branch --show-current)
+if [ "$BRANCH" != "development" ] && [ "$BRANCH" != "main" ]; then
+    warn "Not on development or main branch (current: $BRANCH)"
+    read -p "Continue anyway? [y/N] " -n 1 -r
+    echo
+    if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+        exit 1
+    fi
+fi
+
+# Check [Unreleased] section has content
+if ! grep -q "## \[Unreleased\]" CHANGELOG.md; then
+    error "CHANGELOG.md missing [Unreleased] section"
+fi
+
+# Check if tag already exists
+if git tag -l | grep -q "^v$VERSION$"; then
+    error "Tag v$VERSION already exists"
+fi
+
+info ""
+info "=== Release v$VERSION ==="
+info ""
+
+# Show what will change
+info "Changes to be made:"
+info "  CHANGELOG.md: [Unreleased] -> [$VERSION] - $DATE"
+info "  README.md: title -> v$VERSION"
+info "  marketplace.json: version -> $VERSION"
+info "  Git: commit + tag v$VERSION"
+info ""
+
+# Preview CHANGELOG [Unreleased] content
+info "Current [Unreleased] content:"
+info "---"
+sed -n '/^## \[Unreleased\]/,/^## \[/p' CHANGELOG.md | head -30
+info "---"
+info ""
+
+read -p "Proceed with release? [y/N] " -n 1 -r
+echo
+if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+    info "Aborted"
+    exit 0
+fi
+
+info ""
+info "Updating files..."
+
+# 1. Update CHANGELOG.md
+# Replace [Unreleased] with [X.Y.Z] - DATE and add new [Unreleased] section
+sed -i "s/^## \[Unreleased\]$/## [Unreleased]\n\n*Changes staged for the next release*\n\n---\n\n## [$VERSION] - $DATE/" CHANGELOG.md
+
+# Remove the placeholder text if it exists after the new [Unreleased]
+sed -i '/^\*Changes staged for the next release\*$/d' CHANGELOG.md
+
+# Clean up any double blank lines
+sed -i '/^$/N;/^\n$/d' CHANGELOG.md
+
+success "  CHANGELOG.md updated"
+
+# 2. Update README.md title
+sed -i "s/^# Leo Claude Marketplace - v[0-9]\+\.[0-9]\+\.[0-9]\+$/# Leo Claude Marketplace - v$VERSION/" README.md
+success "  README.md updated"
+
+# 3. Update marketplace.json version
+sed -i "s/\"version\": \"[0-9]\+\.[0-9]\+\.[0-9]\+\"/\"version\": \"$VERSION\"/" .claude-plugin/marketplace.json
+success "  marketplace.json updated"
+
+info ""
+info "Files updated. Review changes:"
+info ""
+git diff --stat
+info ""
+git diff CHANGELOG.md | head -40
+info ""
+
+read -p "Commit and tag? [y/N] " -n 1 -r
+echo
+if [[ ! $REPLY =~ ^[Yy]$ ]]; then
+    warn "Changes made but not committed. Run 'git checkout -- .' to revert."
+    exit 0
+fi
+
+# Commit
+git add CHANGELOG.md README.md .claude-plugin/marketplace.json
+git commit -m "chore: release v$VERSION"
+success "  Committed"
+
+# Tag
+git tag "v$VERSION"
+success "  Tagged v$VERSION"
+
+info ""
+success "=== Release v$VERSION created ==="
+info ""
+info "Next steps:"
+info "  1. Review the commit: git show HEAD"
+info "  2. Push to remote: git push && git push --tags"
+info "  3. Merge to main if on development branch"
+info ""

scripts/setup.sh

@@ -116,6 +116,15 @@ verify_symlinks() {
         log_error "pr-review/gitea symlink missing"
         log_todo "Run: ln -s ../../../mcp-servers/gitea plugins/pr-review/mcp-servers/gitea"
     fi
+
+    # Check data-platform -> data-platform symlink
+    local dataplatform_link="$REPO_ROOT/plugins/data-platform/mcp-servers/data-platform"
+    if [[ -L "$dataplatform_link" ]]; then
+        log_success "data-platform symlink exists"
+    else
+        log_error "data-platform symlink missing"
+        log_todo "Run: ln -s ../../../mcp-servers/data-platform plugins/data-platform/mcp-servers/data-platform"
+    fi
 }
 
 # --- Section 3: Config File Templates ---
@@ -178,6 +187,22 @@ EOF
         chmod 600 "$config_dir/git-flow.env"
         log_success "git-flow.env template created"
     fi
+
+    # PostgreSQL config (for data-platform, optional)
+    if [[ -f "$config_dir/postgres.env" ]]; then
+        log_skip "postgres.env already exists"
+    else
+        cat > "$config_dir/postgres.env" << 'EOF'
+# PostgreSQL Configuration (for data-platform plugin)
+# Update with your PostgreSQL connection URL
+# This is OPTIONAL - pandas tools work without it
+
+POSTGRES_URL=postgresql://user:password@localhost:5432/database
+EOF
+        chmod 600 "$config_dir/postgres.env"
+        log_success "postgres.env template created"
+        log_todo "Edit ~/.config/claude/postgres.env with your PostgreSQL credentials (optional)"
+    fi
 }
 
 # --- Section 4: Validate Configuration ---
@@ -283,6 +308,7 @@ main() {
     # Shared MCP servers at repository root
     setup_shared_mcp "gitea"
     setup_shared_mcp "netbox"
+    setup_shared_mcp "data-platform"
 
     # Verify symlinks from plugins to shared MCP servers
     verify_symlinks

scripts/validate-marketplace.sh

@@ -168,6 +168,12 @@ if [[ ! -d "$ROOT_DIR/mcp-servers/netbox" ]]; then
 fi
 echo "✓ Shared netbox MCP server exists"
 
+if [[ ! -d "$ROOT_DIR/mcp-servers/data-platform" ]]; then
+    echo "ERROR: Shared data-platform MCP server not found at mcp-servers/data-platform/"
+    exit 1
+fi
+echo "✓ Shared data-platform MCP server exists"
+
 # Check symlinks for plugins that use MCP servers
 check_mcp_symlink() {
     local plugin_name="$1"
@@ -195,5 +201,8 @@ check_mcp_symlink "pr-review" "gitea"
 # Plugins with netbox MCP dependency
 check_mcp_symlink "cmdb-assistant" "netbox"
 
+# Plugins with data-platform MCP dependency
+check_mcp_symlink "data-platform" "data-platform"
+
 echo ""
 echo "=== All validations passed ==="

scripts/verify-hooks.sh

@@ -0,0 +1,44 @@
+#!/bin/bash
+# Verify all hooks are command type (not prompt)
+# Run this after any plugin update
+
+echo "=== HOOK VERIFICATION ==="
+echo ""
+
+FAILED=0
+
+# Check ALL hooks.json files in .claude directory
+for f in $(find ~/.claude -name "hooks.json" 2>/dev/null); do
+    if grep -q '"type": "prompt"' "$f" || grep -q '"type":"prompt"' "$f"; then
+        echo "❌ PROMPT HOOK FOUND: $f"
+        FAILED=1
+    fi
+done
+
+# Note about cache (informational only - do NOT clear mid-session)
+if [ -d ~/.claude/plugins/cache/leo-claude-mktplace ]; then
+    echo "ℹ️  Cache exists: ~/.claude/plugins/cache/leo-claude-mktplace"
+    echo "   (This is normal - do NOT clear mid-session or MCP tools will break)"
+    echo "   To apply plugin changes: restart Claude Code session"
+fi
+
+# Verify installed hooks are command type
+for plugin in doc-guardian code-sentinel projman pr-review project-hygiene data-platform; do
+    HOOK_FILE=~/.claude/plugins/marketplaces/leo-claude-mktplace/plugins/$plugin/hooks/hooks.json
+    if [ -f "$HOOK_FILE" ]; then
+        if grep -q '"type": "command"' "$HOOK_FILE" || grep -q '"type":"command"' "$HOOK_FILE"; then
+            echo "✓ $plugin: command type"
+        else
+            echo "❌ $plugin: NOT command type"
+            FAILED=1
+        fi
+    fi
+done
+
+echo ""
+if [ $FAILED -eq 0 ]; then
+    echo "✓ All hooks verified OK"
+else
+    echo "❌ ISSUES FOUND - fix before using"
+    exit 1
+fi