FastMCP

A fast, lightweight, and high-performance Model Context Protocol (MCP) server implementation designed for seamless AI tool integration.

🚀 Features

• High Performance: Optimized for low latency and minimal overhead.

• Easy Integration: Seamlessly connects your custom tools and data sources to LLMs.

• Lightweight: Minimal dependencies to keep your environment clean.

• Developer Friendly: Simple setup with intuitive API patterns.

Related MCP server: Search MCP Server

🛠️ Installation

Choose the installation command based on your package manager:

# Using pip
pip install fastmcp

# Using npm
npm install fastmcp

💻 Quick Start

Here is a quick example to get your FastMCP server up and running:

from fastmcp import FastMCP

# Initialize the server
server = FastMCP("My FastMCP Server")

# Define a custom tool
@server.tool()
def calculate_metrics(a: int, b: int) -> str:
    """Performs a quick high-performance calculation."""
    return f"Result: {a * b}"

if __name__ == "__main__":
    server.run()

⚙️ Configuration

Configure your server connection in your LLM client settings (e.g., Claude Desktop claude_desktop_config.json):

{
  "mcpServers": {
    "fastmcp": {
      "command": "python",
      "args": ["path/to/your/server.py"]
    }
  }
}

📄 License

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