docmind-parser-mcp 0.1.1

An MCP server for the 'docmind_parser' library.

MCP 服务构建

包构建

1、cd docmind-parse-mcp && uv build 3、上传oss或者pypi

测试

• 其他mcp client

{
  "mcpServers": {
    "markitdown": {
      "name": "docmind-parser-mcp",
      "command": "uvx",
      "args": [
        "--with",
        "https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/sdk/doc_json_sdk-1.0.3-py3-none-any.whl",
        "--with",
        "https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/sdk/docmind_parser_mcp-0.1.1-py3-none-any.whl",
        "docmind-parser-mcp"
      ],
      "env": {
        "SERVER_PROTOCOL_MODE": "stdio",
        "ALIBABA_CLOUD_ACCESS_KEY_ID": "YOUR_ALIBABA_CLOUD_ACCESS_KEY_ID",
        "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "YOUR_ALIBABA_CLOUD_ACCESS_KEY_SECRET"
      }
    }
  }
}

• uvx 测试

uvx --with 'https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/sdk/doc_json_sdk-1.0.3-py3-none-any.whl' --with "https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/sdk/docmind_parser_mcp-0.1.1-py3-none-any.whl"  docmind-parser-mcp

• python 脚本测试

import asyncio

from mcp.client.stdio import stdio_client
from mcp import ClientSession, StdioServerParameters

# 为 stdio 连接创建服务器参数
server_params = StdioServerParameters(
    # 服务器执行的命令，这里我们使用 uv 来运行 web_search.py
    command='uvx',
    # 运行的参数
    args=['--with', 'https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/sdk/doc_json_sdk-1.0.3-py3-none-any.whl',
          '--with', 'https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/sdk/docmind_parser_mcp-0.1.1-py3-none-any.whl',
          'docmind-parser-mcp'],
    # 环境变量，默认为 None，表示使用当前环境变量
    env={
        "ALIBABA_CLOUD_ACCESS_KEY_ID": "YOUR_ALIBABA_CLOUD_ACCESS_KEY_ID",
        "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "YOUR_ALIBABA_CLOUD_ACCESS_KEY_SECRET"
    }
)
async def main():
    # 创建 stdio 客户端
    async with stdio_client(server_params) as (stdio, write):
        # 创建 ClientSession 对象
        async with ClientSession(stdio, write) as session:
            # 初始化 ClientSession
            await session.initialize()

            # 列出可用的工具
            response = await session.list_tools()
            print(response)

            # 调用工具
            response = await session.call_tool('convert_to_markdown', {'uri': 'https://duguang-guji.oss-cn-hangzhou.aliyuncs.com/tmp/test2.md'})
            print(response)


if __name__ == '__main__':
    asyncio.run(main())

docmind-parser-mcp 是一个 Python 包和命令行实用程序，用于将各种文件转换为 Markdown（例如，用于索引、文本分析等）。

支持的文档格式：pdf、word、ppt、pptx、【xls、xlsx、xlsm】和图片，图片支持jpg、jpeg、png、bmp、gif，其余格式支持markdown、html、epub、mobi、rtf、txt

支持本地文件和url文件两种方式

源码构建： 1.安装依赖 cd到docmind-parser-mcp项目目录下 pip install . 2.服务启动之前必须设置的相关环境变量 1.该命令行程序依赖阿里云文档智能解析的能力，所以，需要进行开通，获取AccessKey ID、AccessKey Secret，设置环境变量。 export ALIBABA_CLOUD_ACCESS_KEY_SECRET=YOUR_ALIBABA_CLOUD_ACCESS_KEY_SECRET export ALIBABA_CLOUD_ACCESS_KEY_ID=YOUR_ALIBABA_CLOUD_ACCESS_KEY_ID 2.设置mcp的启动模式SERVER_PROTOCOL_MODE ,有两种可选模式 [stdio | sse] stdio模式：该模式只需要设置一个环境变量 export SERVER_PROTOCOL_MODE=stdio 3.启动服务 python -m docmind_parser_mcp._docmind_mcp.py

mcp服务器（使用镜像），配置mcp-server的配置文件 本地源码构建配置stdio： { "mcpServers": { "docmind-parser-mcp": { "name": "docmind-parser-mcp", "command": "uv",#本地uv命令。 "args": [ "--directory", "/Users/chengshuai/PycharmProjects/docmind-parser-mcp/src/docmind_parser_mcp",# 项目路径 "run", "server.py" ], "env": { "SERVER_PROTOCOL_MODE": "stdio", "ALIBABA_CLOUD_ACCESS_KEY_ID": "YOUR_ALIBABA_CLOUD_ACCESS_KEY_ID", "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "YOUR_ALIBABA_CLOUD_ACCESS_KEY_SECRET" } } } }

python项目已提交到pipy。 stdio模式 { "mcpServers": { "markitdown": { "name": "docmind-parser-mcp", "command": "uvx", "args": [ "docmind-parser-mcp" ], "env": { "SERVER_PROTOCOL_MODE": "stdio", "ALIBABA_CLOUD_ACCESS_KEY_ID": "YOUR_ALIBABA_CLOUD_ACCESS_KEY_ID", "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "YOUR_ALIBABA_CLOUD_ACCESS_KEY_SECRET" } } } }

远程配置sse模式 { "mcpServers": { "markitdown": { "url":"http://xxxx/sse", "transportType": "sse" } } }