search_docs_mcp

Overview

Search Docs MCP is a tool designed to solve the problem of outdated knowledge in AI assistants. It enables semantic search across multiple AI library documentations including LangChain, LangGraph, CrewAI, LlamaIndex, and OpenAI. The tool uses the Serper API for efficient web search and provides a configuration system for easy addition of new documentation sources.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• get_docsquery: str, library: str

  Search documentation for a specific query in a given library.

  Try:Search for Chroma DB in LangChain documentationTry:How to use CrewAI in the CrewAI libraryTry:Find information about OpenAI API models

Comparable tools

Installation

# Clone the repository
git clone https://github.com/mostafa-ghaith/search-docs-mcp.git
cd search-docs-mcp

# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate

# Install dependencies
pip install -e .

# Create .env file with API key
echo "SERPER_API_KEY=your_api_key_here" > .env

{
  "mcpServers": {
    "search-docs-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/YOUR/search-docs-mcp",
        "run",
        "main.py"
      ]
    }
  }
}

FAQ

What search API does this MCP server use?

It uses the Serper API for web search functionality.

How do I add a new documentation source?

Edit the config.py file to add your new library URL and description to the DOCS_CONFIG dictionary.

Compare search_docs_mcp with