• 🔍 Smart Documentation Search - Search across multiple AI/ML library documentation
• 🧠 Claude Integration - Seamless connection with Claude's advanced reasoning capabilities
• 🌐 Intelligent Web Search - Leverages Serper API for targeted documentation lookup
• 💨 Fast Response Times - Optimized for quick retrieval and processing
• 🧩 Extendable Architecture - Easily add more documentation sources

• 🐍 Python 3.8 or higher
• 🔑 Claude Pro subscription
• 🔐 Serper API key (Get one here)
• 💻 Claude Desktop application

# Clone the repository
git clone https://github.com/your-username/claude-docs-assistant.git
cd claude-docs-assistant

# Create a virtual environment (recommended)
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

Create a .env file in the project root with your API keys:

SERPER_API_KEY=your_serper_api_key_here

python main.py

You should see output indicating the server is running and waiting for Claude to connect.

1. 📱 Open the Claude Desktop App
2. ⚙️ Click on your profile icon and select "Settings"
3. 🧰 Navigate to the "Tools" section
4. ➕ Click "Add Tool"
5. 🔗 Select "Connect to a local tool"
6. 🖥️ Follow the prompts to connect to your running MCP server
7. ✅ Confirm the connection is successful

Once connected, you can start asking Claude questions that will trigger the documentation search. For example:

Could you explain how to use FAISS with LangChain? Please search the langchain documentation to help me.

Claude will automatically use your MCP server to:

1. 🔍 Search for relevant documentation
2. 📥 Retrieve the content
3. 🧠 Process and explain the information

claude-docs-assistant/
├── main.py           # MCP server implementation
├── requirements.txt  # Project dependencies
├── .env              # Environment variables (API keys)
└── README.md         # This documentation

The assistant currently supports searching documentation for:

• 🦜 LangChain: python.langchain.com/docs
• 🦙 LlamaIndex: docs.llamaindex.ai/en/stable
• 🧠 OpenAI: platform.openai.com/docs

1. 📡 The MCP server exposes a get_docs tool to Claude
2. 🔍 When invoked, the tool searches for documentation using Serper API
3. 📚 Results are scraped for their content
4. 🔄 Content is returned to Claude for analysis and explanation

Extend the docs_urls dictionary in main.py:

docs_urls = {
    "langchain": "python.langchain.com/docs",
    "llama-index": "docs.llamaindex.ai/en/stable",
    "openai": "platform.openai.com/docs",
    "huggingface": "huggingface.co/docs",  # Add new documentation sources
    "tensorflow": "www.tensorflow.org/api_docs",
}

Modify the search_web function to adjust the number of results:

payload = json.dumps({"q": query, "num": 5})  # Increase from default 2

• 🚫 "Connection refused" error: Ensure the MCP server is running before connecting Claude
• ⏱️ Timeout errors: Check your internet connection or increase the timeout value
• 🔒 API key issues: Verify your Serper API key is correct in the .env file

Add more detailed logging by modifying the main.py file:

import logging
logging.basicConfig(level=logging.DEBUG)

• ⚡ For faster response times, consider caching frequently accessed documentation
• 🧠 Limit the amount of text returned to Claude to avoid token limitations
• 🌐 Use more specific queries to get more relevant documentation

Contributions are welcome! Here's how you can help:

1. 🍴 Fork the repository
2. 🌿 Create a feature branch (git checkout -b feature/amazing-feature)
3. 💾 Commit your changes (git commit -m 'Add some amazing feature')
4. 📤 Push to the branch (git push origin feature/amazing-feature)
5. 🔍 Open a Pull Request

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

• Anthropic for creating Claude
• Serper.dev for their search API
• All the open-source libraries that make this project possible