MCP Run Python

MCP Run Python

Model Context Protocol server to run Python code in a sandbox.

The code is executed using Pyodide in Deno and is thereforeisolated from the rest of the operating system.

See https://ai.pydantic.dev/mcp/run-python/ for complete documentation.

The server can be run with deno installed using:

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

where:

• -N -R=node_modules -W=node_modules (alias of--allow-net --allow-read=node_modules --allow-write=node_modules) allowsnetwork access and read+write access to ./node_modules. These are requiredso pyodide can download and cache the Python standard library and packages
• --node-modules-dir=auto tells deno to use a local node_modules directory
• stdio runs the server with theStdio MCP transport— suitable for running the process as a subprocess locally
• sse runs the server with theSSE MCP transport— running the server as an HTTP server to connect locally or remotely
• warmup will run a minimal Python script to download and cache the Pythonstandard library. This is also useful to check the server is runningcorrectly.

Here's an example of using @pydantic/mcp-run-python with PydanticAI:

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.data)
    #> There are 9,208 days between January 1, 2000, and March 18, 2025.w

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