mcp-server-documentation

A powerful documentation search server built with FastMCP, enabling AI systems to intelligently search across multiple popular framework and library documentations. This tool ensures that AI models can quickly access and retrieve relevant information from various documentation sources using a unified interface.

• 📚 Multi-Library Support: Search documentation across multiple libraries:

  • LangChain - JavaScript/TypeScript LangChain documentation
  • LangGraph - LangGraph.js documentation
  • Next.js - Next.js framework documentation
  • Tailwind CSS - Utility-first CSS framework
  • FastMCP - FastMCP documentation
  • Framer Motion - Animation library for React

• 🔍 Intelligent Search

  • Smart name resolution for library variations
  • DuckDuckGo-powered search for accurate results
  • Site-specific search targeting

• ⚡ Performance Features

  • Asynchronous processing
  • Efficient web request handling
  • Parallel content fetching

• 🛡️ Robust Error Handling

  • Network timeout management
  • Invalid input validation
  • HTTP error handling
  • Request failure recovery

• Python 3.8+
• pip or uv package manager
• Virtual environment (recommended)

1. Clone the Repository

git clone <repository-url>
cd mcp-server

2. Set Up Virtual Environment

python -m venv .venv
# On Windows:
.venv\Scripts\activate
# On Unix or MacOS:
source .venv/bin/activate

3. Install Dependencies

pip install -r requirements.txt

4. Run the Server

python main.py

from main import get_docs

# Search Framer Motion documentation
result = await get_docs(
    query="how to animate on scroll",
    library="framer-motion"
)

# Search Next.js documentation
result = await get_docs(
    query="how to use app router",
    library="next"
)

The system intelligently handles various library name formats:

# All these calls will work the same way
await get_docs(query="animations", library="framer")
await get_docs(query="animations", library="framermotion")
await get_docs(query="animations", library="framer-motion")
await get_docs(query="animations", library="motion")

The project includes a comprehensive test suite to ensure reliability and correctness. Tests are organized into three main categories:

• Unit Tests: Test individual components in isolation

  • test_utils.py: Tests for library name normalization and URL retrieval
  • test_services.py: Tests for web search and content fetching services

• Integration Tests: Test how components work together

  • test_main.py: Tests for the main API function get_docs

To run all tests:

python -m pytest

To run specific test modules:

python -m pytest tests/test_utils.py
python -m pytest tests/test_services.py
python -m pytest tests/test_main.py

To run tests with verbose output:

python -m pytest -v

The tests cover:

• ✅ Library name normalization and validation
• ✅ URL retrieval for different libraries
• ✅ Web search functionality
• ✅ Content fetching and error handling
• ✅ Documentation search integration
• ✅ API input validation and error handling
• ✅ Alias resolution for different library name formats

The project uses a custom run_async helper function to test asynchronous code in a synchronous test environment. This approach allows for testing async functions without requiring complex test setup.

mcp-server/
├── main.py          # Entry point and FastMCP tool definition
├── config.py        # Configuration settings and constants
├── services.py      # Web search and content fetching services
├── utils.py         # Utility functions for library name handling
├── tests/           # Test suite
│   ├── test_utils.py    # Tests for utility functions
│   ├── test_services.py # Tests for web services
│   ├── test_main.py     # Tests for main API
│   └── conftest.py      # Pytest configuration
├── requirements.txt # Project dependencies
└── README.md        # Documentation

To add a new library:

1. Add the documentation URL in config.py:

DOCS_URLS = {
    "new-library": "https://docs.new-library.com",
    # ... existing entries
}

2. Add common aliases:

LIBRARY_ALIASES = {
    "new-lib": "new-library",
    # ... existing entries
}

Modify in config.py:

HTTP_TIMEOUT = 30.0        # Timeout in seconds
MAX_SEARCH_RESULTS = 2     # Number of search results to fetch

We welcome contributions! Here's how you can help:

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests for new functionality
5. Ensure all tests pass
6. Submit a pull request

1. Update DOCS_URLS in config.py
2. Add relevant aliases in LIBRARY_ALIASES
3. Test the integration
4. Update documentation
5. Submit a pull request

Common issues and solutions:

• TimeoutError: Increase HTTP_TIMEOUT in config.py
• No Results: Try different search terms or verify the library name
• HTTP Errors: Check your internet connection and the documentation URL

This project is licensed under the MIT License - see the LICENSE file for details.

• FastMCP for the core functionality
• DuckDuckGo for search capabilities
• pytest for testing framework
• All supported documentation providers