Cover image
Try Now
2025-03-08

Easy-to-use MCP server framework specialized for SSE.

3 years

Works with Finder

1

Github Watches

6

Github Forks

17

Github Stars

ezmcp

Easy-to-use MCP server framework specialized for SSE.

Overview

ezmcp is a lightweight framework that makes it easy to create MCP-compatible servers using a FastAPI-like syntax. It provides a simple decorator-based API for defining tools that can be called by MCP clients.

Features

  • FastAPI-style decorator API for defining MCP tools
  • Automatic parameter validation and type conversion
  • Automatic generation of tool schemas from function signatures
  • Built-in support for SSE transport
  • FastAPI-style middleware support
  • Easy integration with existing Starlette applications
  • Interactive documentation page for exploring and testing tools

docs_image

Installation

pip install ezmcp

Quick Start

from ezmcp import ezmcp, TextContent

# Create an ezmcp application
app = ezmcp("my-app")

# Define a tool
@app.tool(description="Echo a message back to the user")
async def echo(message: str):
    """Echo a message back to the user."""
    return [TextContent(type="text", text=f"Echo: {message}")]

# Run the application
if __name__ == "__main__":
    app.run(host="0.0.0.0", port=8000)

Once the server is running, you can:

  • Access the interactive documentation at http://localhost:8000/docs
  • Connect to the SSE endpoint at http://localhost:8000/sse

Middleware

ezmcp supports middleware similar to FastAPI, allowing you to add behavior that is applied across your entire application.

from starlette.requests import Request

from ezmcp import TextContent, ezmcp

app = ezmcp("my-app")

@app.middleware
async def process_time_middleware(request: Request, call_next):
    """Add a header with the processing time."""
    import time
    start_time = time.perf_counter()
    response = await call_next(request)
    process_time = time.perf_counter() - start_time
    response.headers["X-Process-Time"] = str(process_time)
    return response

@app.tool(description="Echo a message back to the user")
async def echo(message: str):
    """Echo a message back to the user."""
    return [TextContent(type="text", text=f"Echo: {message}")]

For more information on middleware, see the middleware documentation.

Documentation

For more detailed documentation, see the ezmcp/README.md file.

License

MIT

commands

  • install for test pdm install -G test
  • install for dev pdm install -G dev

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Khalid kalib
  • Write professional emails

  • https://tovuti.be
  • Oede knorrepot die vasthoudt an de goeie ouwe tied van 't boerenleven

  • Gil kaminski
  • Make sure you are post-ready before you post on social media

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • momi
  • Provides initial medical assessments and advice.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Yasir Eryilmaz
  • AI scriptwriting assistant for short, engaging video content.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • huahuayu
  • A unified API gateway for integrating multiple etherscan-like blockchain explorer APIs with Model Context Protocol (MCP) support for AI assistants.

  • deemkeen
  • control your mbot2 with a power combo: mqtt+mcp+llm

  • zhaoyunxing92
  • 本项目是一个钉钉MCP(Message Connector Protocol)服务,提供了与钉钉企业应用交互的API接口。项目基于Go语言开发,支持员工信息查询和消息发送等功能。

  • justmywyw
  • Short and sweet example MCP server / client implementation for Tools, Resources and Prompts.

  • KasarLabs
  • Build powerful and secure AI Agents powered by Starknet.

    Reviews

    2 (1)
    Avatar
    user_DaoQO8tR
    2025-04-15

    As a dedicated MCP application user, I find the Mifos X - AI - Model Context Protocol (MCP) for Apache Fineract® by openMF to be incredibly efficient and user-friendly. It seamlessly integrates advanced AI capabilities, enhancing the operational workflows and decision-making processes. Highly recommended for organizations looking to leverage AI in their financial services. Check it out here: https://mcp.so/server/mcp-mifosx/openMF