CaptchaMCP

# 验证码识别 MCP 服务 ## 简介 本项目基于 [ddddocr](https://github.com/sml2h3/ddddocr) 和 [Model Context Protocol (MCP) Python SDK](https://github.com/modelcontextprotocol/python-sdk)，实现了一个通过 MCP 协议对外提供验证码图片识别服务的智能后端。 --- ## 依赖 - ddddocr - mcp[fastmcp] --- ## 安装 1. 克隆本项目 ```bash git clone <your-repo-url> cd <your-project-dir> ``` 2. 安装依赖 ```bash pip install ddddocr mcp[fastmcp] ``` --- ## 使用方法 ### 启动服务端 ```bash python main.py ``` ### 客户端调用示例 ```python from mcp import ClientSession, StdioServerParameters from mcp.client.stdio import stdio_client import asyncio async def main(): server_params = StdioServerParameters( command="python", args=["main.py"], env=None, ) async with stdio_client(server_params) as (read, write): async with ClientSession(read, write) as session: await session.initialize() result = await session.call_tool( "recognize_captcha", arguments={"image_path": "E:/code/bug/service/ocr/captchaImage.jpg"} ) print("识别结果:", result) if __name__ == "__main__": asyncio.run(main()) ``` --- ## 工具接口 - `recognize_captcha(image_path: str)` 识别本地图片验证码，返回内容对象 --- ## 客户端使用 ```json { "mcpServers": { "ocr": { "command": "F:\\AI\\anaconda3\\Scripts\\uv.exe", "args": [ "run", "--with", "mcp", "mcp", "run", "E:\\code\\bug\\service\\ocr\\mcp-server-demo\\main.py" ] } } } ``` ## License MIT