The Documentation Search MCP Server is a unified platform that combines documentation search, security auditing, and project scaffolding capabilities.
Documentation Search & Learning:
Semantic search across 100+ documentation sources with filtering by content type, difficulty, and code examples
Library auto-completion suggestions with optional security scoring
Structured learning paths and curated code examples tailored to experience levels
Documentation cache management and source health monitoring
Security & Vulnerability Management:
Comprehensive vulnerability scanning for individual libraries and project dependencies using multiple sources (OSV, GitHub Advisories, Safety DB, Snyk)
Security score comparisons and quick security overviews
License compliance checking and continuous security monitoring
Local project scanning from files like
pyproject.tomlandrequirements.txt
Project Development:
Generate starter projects from templates (FastAPI, React)
Manage local development environments and services (PostgreSQL, Redis) using Docker Compose
Configuration management for server settings and local development
The server integrates these tools into a single platform for streamlined developer workflows from documentation research to secure project deployment.
Enables searching through Ansible documentation for automation and configuration management solutions
Offers documentation search across Django web framework, making it easier to find information about models, views, and templates
Provides search capabilities for Docker documentation to help with containerization queries
Enables searching through Express.js documentation for web application development in Node.js
Offers documentation search for FastAPI framework to quickly find information about API development
Provides search across Firebase documentation for app development, authentication, and database queries
Enables searching through Flask documentation for Python web development solutions
Offers documentation search for Git version control system commands and workflows
Provides comprehensive search across JavaScript language documentation
Enables searching through Kubernetes documentation for container orchestration
Offers documentation search for LangChain library to help with language model application development
Provides search capabilities for LangGraph documentation for building complex LLM applications
Enables searching through MongoDB documentation for NoSQL database operations and queries
Offers documentation search for Node.js runtime environment
Provides search capabilities for NumPy library documentation for numerical computing in Python
Enables searching through OpenAI's documentation for API usage and model capabilities
Offers documentation search for Pandas data manipulation and analysis library
Provides search across PostgreSQL documentation for database management and SQL queries
Enables searching through Python programming language documentation
Offers documentation search for React library to quickly find information about components and hooks
Provides search capabilities for SQLAlchemy ORM documentation for Python database interactions
Enables searching through Streamlit documentation for building data applications in Python
Offers documentation search for Supabase platform for backend development
Provides search across Terraform documentation for infrastructure as code solutions
Enables searching through Vercel documentation for deployment and hosting solutions
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Documentation Search MCP Serversearch for FastAPI authentication examples"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Documentation Search MCP Server
MCP server for searching documentation, scanning dependencies for vulnerabilities, and generating project boilerplate. Works with Claude Desktop, Cursor, and other MCP clients.
📚 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
Related MCP server: docs-mcp-server
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]==1.9.0Configuration
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@1.9.0With 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@1.9.0Without SERPER API Key (uses prebuilt index from GitHub Releases):
codex mcp add documentation-search-enhanced \
-- /Users/yourusername/.local/bin/uvx documentation-search-enhanced@1.9.0If you get a timeout on first run, pre-download dependencies:
uvx documentation-search-enhanced@1.9.0Environment Variables
SERPER_API_KEY- Optional. Enables live web search. Without it, uses prebuilt index from GitHub Releases.DOCS_SITE_INDEX_AUTO_DOWNLOAD- Set tofalseto disable automatic index downloadsDOCS_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 documentationget_docs- Fetch specific documentationget_learning_path- Generate learning roadmapget_code_examples- Find code snippetsscan_project_dependencies- Vulnerability scansnyk_scan_project- Detailed Snyk analysisgenerate_project_starter- Create project boilerplatemanage_dev_environment- Generate docker-compose filescompare_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.mainTesting
uv run pytest --ignore=pytest-test-project # Core tests
uv run ruff check src # Linting
uv run ruff format src --check # Format checkConfiguration
Use the get_current_config tool to export current settings to config.json. Validate with:
uv run python src/documentation_search_enhanced/config_validator.pyContributing
See CONTRIBUTING.md for guidelines. Use Conventional Commits for commit messages.
License
MIT License - see LICENSE for details.