CAPTCHA识别MCP服务

简介

该项目基于ddddocr和Model Context Protocol (MCP) Python SDK，实现了一个智能后端，通过MCP协议对外提供CAPTCHA图像识别服务。

---

依赖项

• ddddocr
• mcp[fastmcp]

---

安装

1. 克隆此项目

   git clone <your-repo-url>
   cd <your-project-dir>
   

2. 安装依赖项

   pip install ddddocr mcp[fastmcp]
   

---

使用说明

启动服务器

python main.py

客户端调用示例

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)
  识别本地图像CAPTCHA并返回内容对象

---

客户端使用

{
    "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"
            ]
        }
    }
}

许可证

MIT