FastMCP v2 🚀

🚀 The fast, Pythonic way to build MCP servers and clients

Catalog onlyCatalog onlySTDIO

Overview

FastMCP is a Python library designed to simplify the creation of Model Context Protocol (MCP) servers, allowing developers to expose data and functionality to large language models (LLMs) in a standardized way.

To use FastMCP, install it via pip, create a Python script defining your MCP server, and use decorators to add tools and resources. Run the server using the FastMCP CLI commands.

Fast: High-level interface for rapid development. - Simple: Minimal boilerplate code required to build MCP servers. - Pythonic: Intuitive for Python developers, leveraging familiar syntax. - Complete: Aims to provide a full implementation of the MCP specification.

Building interactive tools for LLMs.
Exposing APIs for data retrieval and manipulation.
Creating educational applications that utilize LLMs for enhanced learning experiences.

Add to your AI client

Use these steps to connect FastMCP v2 🚀 in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "fastmcp-jlowin": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fastmcp-jlowin"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "fastmcp-jlowin": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fastmcp-jlowin"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "fastmcp-jlowin": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fastmcp-jlowin"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "fastmcp-jlowin": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fastmcp-jlowin"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "fastmcp-jlowin": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fastmcp-jlowin"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "fastmcp-jlowin": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fastmcp-jlowin"
      ]
    }
  }
}

FAQ

Can FastMCP be used for any LLM?

Yes! FastMCP is designed to work with any LLM that supports the Model Context Protocol.

Is FastMCP free to use?

Yes! FastMCP is open-source and available for free.

How do I contribute to FastMCP?

You can contribute by forking the repository, making changes, and submitting a pull request.

Developer tools