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 therefore isolated 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) allows network access and read+write access to ./node_modules. These are required so 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 the Stdio MCP transport — suitable for running the process as a subprocess locally
sse runs the server with the SSE 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 Python standard library. This is also useful to check the server is running correctly.

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

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

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

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

Related MCP Servers

Blender MCP Server
cwahlfeldt
-
security
F
license
-
quality
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.
Last updated -
8
Nash MCP Server
nash-app
-
security
A
license
-
quality
A Model Context Protocol server that enables seamless execution of commands, Python code, web content fetching, and reusable task management with secure credentials handling.
Last updated -
2
MIT License
MCP Server Python Template
Cris-0k
-
security
A
license
-
quality
A streamlined foundation for building Model Context Protocol servers in Python, designed to make AI-assisted development of MCP tools easier and more efficient.
Last updated -
14
MIT License
MCP Python Server
jatindera
-
security
F
license
-
quality
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.
Last updated -

View all related MCP servers

mcp-run-python

MCP Run Python

Related MCP Servers

Blender MCP Server

Nash MCP Server

MCP Server Python Template

MCP Python Server

Appeared in Searches

New MCP Servers

MCP directory API