This MCP server provides a unified search interface for multiple documentation sources. It aggregates documentation from popular libraries and frameworks such as LangChain, LangGraph, Next.js, Tailwind CSS, FastMCP, and Framer Motion, allowing AI systems to query across these sources with a single API. The server supports intelligent library name handling, so variations like framer, framermotion, or framer-motion are treated equivalently. Searches are powered by a DuckDuckGo-backed strategy with site-specific targeting to yield relevant results quickly. The service is designed for asynchronous operation and parallel content fetching to optimize performance when querying multiple docs in parallel. You can access the main API via the provided Python interface (e.g., calling get_docs with a query and library) to retrieve concise documentation snippets for your AI workflows.

Prerequisites:

• Python 3.8 or newer
• Python's virtual environment tool (recommended)
• Internet access to install dependencies

Step-by-step installation:

1. Clone the repository git clone <repository-url> cd mcp-server

2. Set up a virtual environment python -m venv .venv

   On Windows:

   .venv\Scripts\activate

   On Unix/macOS:

   source .venv/bin/activate

3. Install dependencies pip install -r requirements.txt

4. Configure environment (optional but recommended)

   • Create a .env file or export variables: export HTTP_TIMEOUT=30.0 export MAX_SEARCH_RESULTS=2
   • If using a .env file, load it in your environment before running the server

5. Run the server python main.py

Note: If you modify DOCS_URLS or LIBRARY_ALIASES in config.py for adding new libraries, restart the server to pick up changes.

Tips and common considerations:

• If you encounter timeouts, increase HTTP_TIMEOUT in config.py or via environment variables.
• Adjust MAX_SEARCH_RESULTS to balance result quality with performance.
• Ensure your environment has network access to fetch documentation pages.
• The server supports multiple libraries; to add a new library, update DOCS_URLS and LIBRARY_ALIASES in config.py and restart.
• For debugging, pytest tests can help verify library name normalization and search behavior: python -m pytest
• If using a container deployment, map environment variables appropriately and ensure Python version compatibility.