Skip to main content
Glama
pydantic

mcp-run-python

Official
by pydantic

MCP 运行 Python

模型上下文协议服务器在沙箱中运行 Python 代码。

该代码使用Deno中的Pyodide执行,因此与操作系统的其余部分隔离。

请参阅https://ai.pydantic.dev/mcp/run-python/以获取完整文档。

可以使用以下命令安装deno来运行服务器:

deno run \
  -N -R=node_modules -W=node_modules --node-modules-dir=auto \
  jsr:@pydantic/mcp-run-python [stdio|sse|warmup]

在哪里:

  • -N -R=node_modules -W=node_modules ( --allow-net --allow-read=node_modules --allow-write=node_modules的别名)允许网络访问以及对./node_modules的读写访问。这些是 pyodide 下载和缓存 Python 标准库和软件包所必需的。

  • --node-modules-dir=auto告诉 deno 使用本地node_modules目录

  • stdio使用Stdio MCP 传输运行服务器 - 适合在本地将进程作为子进程运行

  • sse使用SSE MCP 传输运行服务器 — 将服务器作为 HTTP 服务器运行,以便进行本地或远程连接

  • warmup将运行一个精简的 Python 脚本来下载并缓存 Python 标准库。这对于检查服务器是否正常运行也很有用。

以下是使用@pydantic/mcp-run-python与 PydanticAI 的示例:

from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStdio

import logfire

logfire.configure()
logfire.instrument_mcp()
logfire.instrument_pydantic_ai()

server = MCPServerStdio('deno',
    args=[
        'run',
        '-N',
        '-R=node_modules',
        '-W=node_modules',
        '--node-modules-dir=auto',
        'jsr:@pydantic/mcp-run-python',
        'stdio',
    ])
agent = Agent('claude-3-5-haiku-latest', mcp_servers=[server])


async def main():
    async with agent.run_mcp_servers():
        result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
    print(result.output)
    #> There are 9,208 days between January 1, 2000, and March 18, 2025.w

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

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that allows management and execution of Blender Python scripts, enabling users to create, edit and run scripts in a headless Blender environment through natural language interfaces.
    11
    -
  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    A streamlined foundation for building Model Context Protocol servers in Python, designed to make AI-assisted development of MCP tools easier and more efficient.
    12
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    A Python-based implementation of the Model Context Protocol that enables communication between a model context management server and client through a request-response architecture.
    -