FastMCP

Active
GitHub Python Apache-2.0

Description

FastMCP is a fast, Pythonic library for building MCP servers and clients with over 1 million daily downloads, making it easy to create Model Context Protocol tools.

Key Features

  • Decorator-Based Tools — Create MCP tools with Python functions and @mcp.tool decorator, auto-generating schema and docs
  • MCP Client — Connect to any MCP server (local or remote) with full protocol handshake and session management
  • Interactive Apps — Generate interactive UIs for tools that render directly in conversations
  • Auto Transport Negotiation — Automatically handles connection and auth for SSE, stdio, and other transports
  • Type-Safe Validation — Auto-generates parameter validation and error handling from Python type annotations
  • Production-Grade Deployment — Integrates with Prefect Horizon for SSO, RBAC, audit logs, and observability

Use Cases

💡 Quickly wrapping Python functions as MCP tools for LLMs to call
💡 Building MCP servers exposing database queries, file operations to AI agents
💡 Connecting to existing tool servers via MCP client to add AI capabilities to applications
💡 Creating interactive MCP apps with Web UIs for internal toolchains
💡 Securely deploying and managing multiple MCP servers in production environments

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (27.5k stars)
  • Permissive open-source license (Apache-2.0)

Categories

Quick Start

uv pip install fastmcp

from fastmcp import FastMCP

mcp = FastMCP("Demo")

@mcp.tool
def add(a: int, b: int) -> int:
    """Add two numbers"""
    return a + b

@mcp.tool
def search_files(query: str) -> str:
    """Search for files matching a query"""
    import subprocess
    result = subprocess.run(["find", ".", "-name", query], capture_output=True, text=True)
    return result.stdout

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

Related Projects

AWS MCP Servers

9.7k · Python
Active A

Official MCP server collection from AWS, providing AI agents with integration to core AWS services including Lambda, S3, DynamoDB, and Bedrock.

mcpawscloud +2
  • · Official suite of MCP servers from AWS — providing AI agents access to AWS documentation, best practices, and service integration
  • · Covers core AWS services including Lambda, S3, DynamoDB, Bedrock, SQS, SNS, Step Functions, and more
  • · Supports multiple AI clients — Claude Desktop, Cursor, VS Code, Windsurf, Kiro, and any MCP-compatible agent

MCP Use

10.6k · TypeScript
Active A+

MCP Use is a Model Context Protocol orchestration project that helps agents connect to MCP servers, unify tool invocation, and improve portability across toolchains.

mcptoolsprotocol +1
  • · Fullstack MCP framework with SDK for both TypeScript and Python
  • · Build MCP Servers with typed tool definitions and Zod schema validation
  • · MCP Apps — interactive React widgets that work across Claude, ChatGPT, and other clients

MCP Python SDK

24.2k · Python
Active A+

MCP Python SDK is the official Python implementation for building MCP servers and agent-side integrations with a standardized tool protocol.

mcppythonsdk +1
  • · FastMCP high-level interface — quickly define MCP Server tools, resources and prompts with decorators
  • · Multi-transport support — supports stdio, SSE and Streamable HTTP standard transport methods
  • · Structured output — tool return values automatically serialized into structured JSON responses

Awesome Claude Skills

74.3k · Python
Active A

A curated list of awesome Claude Skills, resources and tools for customizing Claude AI workflows.

mcptoolspython +1
  • · 1000+ production-ready skills - Covering 9 categories including document processing, dev tools, data analysis, marketing, and writing
  • · Cross-agent compatible - Works with Claude Code, Claude.ai, OpenAI Codex, Cursor, Gemini CLI, Windsurf and more
  • · Progressive loading architecture - Each skill loads only name and description (~100 tokens), full content on demand, hundreds coexist

Related Articles