python-mcp-server-client

Overview

This MCP server provides a unified interface to access documentation for popular AI frameworks including LangChain, LlamaIndex, AutoGen, Agno, OpenAI Agents SDK, MCP-doc, Camel-AI, and Crew-AI. It implements both stdio and SSE transport protocols, making it suitable for both local and cloud deployments. The server uses web scraping to fetch documentation from official sources, supporting keyword-based searches across multiple frameworks.

Try asking AI

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

• get_docsasync def get_docs(query: str, library: str)

  Search and retrieve documentation for specified AI frameworks

  Try:Get documentation for React Agent in agno frameworkTry:Search for information about memory management in langchainTry:Find documentation about crew-ai team formation

Comparable tools

Installation

# MacOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

uv init mcp-server
cd mcp-server
uv venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
uv add "mcp[cli]" httpx

{
  "mcpServers": {
    "docs-server": {
      "command": "uv",
      "args": [
        "--directory",
        "<your-project-path>",
        "run",
        "main.py"
      ]
    }
  }
}

FAQ

What frameworks are supported?

Currently supports LangChain, LlamaIndex, AutoGen, Agno, OpenAI Agents SDK, MCP-doc, Camel-AI, and Crew-AI.

Which transport protocols does it support?

Supports both stdio for local use and SSE (Server-Sent Events) for cloud deployments.

Compare python-mcp-server-client with