Skip to main content

Documentation Search MCP Server

CI Security Scan PyPI version Python 3.12+ License: MIT

MCP server for searching documentation, scanning dependencies for vulnerabilities, and generating project boilerplate. Works with Claude Desktop, Cursor, and other MCP clients.

📚 Read the comprehensive tutorial for detailed examples and workflows.

Features

  • Search 190+ curated documentation sources with optional semantic vector search
  • Scan Python projects for vulnerabilities (Snyk, Safety, OSV)
  • Generate FastAPI and React project starters
  • Learning paths and code examples

Installation

# Recommended: use uvx (install uv from https://docs.astral.sh/uv)
uvx documentation-search-enhanced@1.9.0

# Or with pip in a virtual environment
pip install documentation-search-enhanced==1.9.0

# Optional: AI semantic search (Python 3.12 only, adds ~600MB)
pip install documentation-search-enhanced[vector]==1.9.0

Configuration

Claude Desktop

Find your uvx path: which uvx

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "documentation-search-enhanced": {
      "command": "/Users/yourusername/.local/bin/uvx",
      "args": ["documentation-search-enhanced@1.9.0"],
      "env": {
        "SERPER_API_KEY": "optional_key_here"
      }
    }
  }
}

Replace /Users/yourusername/.local/bin/uvx with your actual uvx path.

Codex CLI

# Find your uvx path first
which uvx

# Then add with full path (replace with your actual path)
codex mcp add documentation-search-enhanced \
  -- /Users/yourusername/.local/bin/uvx documentation-search-enhanced@1.9.0

# Or if uvx is in PATH:
codex mcp add documentation-search-enhanced \
  -- uvx documentation-search-enhanced@1.9.0

With SERPER API Key (enables live web search):

codex mcp add documentation-search-enhanced \
  --env SERPER_API_KEY=your_key_here \
  -- /Users/yourusername/.local/bin/uvx documentation-search-enhanced@1.9.0

Without SERPER API Key (uses prebuilt index from GitHub Releases):

codex mcp add documentation-search-enhanced \
  -- /Users/yourusername/.local/bin/uvx documentation-search-enhanced@1.9.0

If you get a timeout on first run, pre-download dependencies:

uvx documentation-search-enhanced@1.9.0

Environment Variables

  • SERPER_API_KEY - Optional. Enables live web search. Without it, uses prebuilt index from GitHub Releases.
  • DOCS_SITE_INDEX_AUTO_DOWNLOAD - Set to false to disable automatic index downloads
  • DOCS_SITE_INDEX_PATH - Custom path for documentation index

Set server_config.features.real_time_search=false in your config to disable live crawling.

Semantic Search (Optional)

The [vector] extra adds semantic search using sentence-transformers (all-MiniLM-L6-v2) with hybrid reranking:

  • 50% semantic similarity (cosine)
  • 30% keyword matching
  • 20% source authority

Only works on Python 3.12 (PyTorch limitation). Python 3.13 users get keyword-based search.

To disable vector search even when installed:

semantic_search(query="FastAPI auth", libraries=["fastapi"], use_vector_rerank=False)

Available Tools

Core MCP tools:

  • semantic_search - Search documentation
  • get_docs - Fetch specific documentation
  • get_learning_path - Generate learning roadmap
  • get_code_examples - Find code snippets
  • scan_project_dependencies - Vulnerability scan
  • snyk_scan_project - Detailed Snyk analysis
  • generate_project_starter - Create project boilerplate
  • manage_dev_environment - Generate docker-compose files
  • compare_library_security - Compare library vulnerabilities

Development

git clone https://github.com/anton-prosterity/documentation-search-mcp.git
cd documentation-search-mcp
uv sync --all-extras
uv run python -m documentation_search_enhanced.main

Testing

uv run pytest --ignore=pytest-test-project  # Core tests
uv run ruff check src                       # Linting
uv run ruff format src --check              # Format check

Configuration

Use the get_current_config tool to export current settings to config.json. Validate with:

uv run python src/documentation_search_enhanced/config_validator.py

Contributing

See CONTRIBUTING.md for guidelines. Use Conventional Commits for commit messages.

License

MIT License - see LICENSE for details.

Release files for documentation-search-enhanced 1.9.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for documentation-search-enhanced 1.9.0
File Size Uploaded
documentation_search_enhanced-1.9.0.tar.gz 78.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for documentation-search-enhanced 1.9.0
File Interpreter ABI Platform
documentation_search_enhanced-1.9.0-py3-none-any.whl Python 3 none any Details

Total release size: 163.9 kB

Release files / documentation_search_enhanced-1.9.0.tar.gz

Download URL documentation_search_enhanced-1.9.0.tar.gz
Size 78.1 kB
Tags Source
SHA-256 checksum
How to use checksums
b0da6534c99a1eb2e2aec7afbc5a0bd02162436367eedad857fd117e487b68f2
BLAKE2b-256 checksum
How to use checksums
4dfa832a44a0aca24f61043a5b6a2304261646f2e900fada472badc31f6fa75d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Dec 20, 2025.

Transparency log

Release files / documentation_search_enhanced-1.9.0-py3-none-any.whl

Download URL documentation_search_enhanced-1.9.0-py3-none-any.whl
Size 85.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
73c5bdddfbbfcc15565c512b925d33bbe47541b4ba837a1aebd9a01fda12dea4
BLAKE2b-256 checksum
How to use checksums
3cea0ee05994e3cea8a828459b8062b1d2ef89395f7c98002ebf0b1145d31ed6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Dec 20, 2025.

Transparency log

Release history Release notifications | RSS feed

This release

1.9.0 This release

2 release files

1.8.0

2 release files

1.6.3

2 release files

1.6.2

2 release files

1.6.1

2 release files

1.4.1

2 release files

1.3.2

2 release files

1.3.1

2 release files

1.3.0

2 release files

1.2.0

2 release files

1.1.0

2 release files

1.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page