Python Sandbox MCP server

This server provides a Model Context Protocol (MCP) implementation for executing Python code in a sandboxed environment. It uses Pyodide in Deno, ensuring the code runs in isolation from your operating system for security.

Installation Requirements

To run the MCP Python server, you'll need Deno installed on your system. The server executes Python code through Pyodide which runs in a Deno environment.

Running the Server

You can run the server using Deno with the following command:

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

The command options are:

• -N -R=node_modules -W=node_modules: Allows network access and read/write access to the ./node_modules directory
• --node-modules-dir=auto: Instructs Deno to use a local node_modules directory
• The final argument specifies the transport method:
  • stdio: Uses the Stdio MCP transport (for running as a subprocess locally)
  • sse: Uses the SSE MCP transport (runs an HTTP server for local or remote connections)
  • warmup: Downloads and caches the Python standard library (useful for testing)

Usage with Pydantic AI

Here's an example of how to use the MCP Python server with Pydantic AI:

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', toolsets=[server])


async def main():
    async with agent:
        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.

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

This example demonstrates:

1. Setting up a Pydantic AI agent with the MCP Python server
2. Running the agent with a query that requires Python date calculations
3. Getting the result that was computed in the sandboxed Python environment

Additional Resources

For complete documentation, visit https://ai.pydantic.dev/mcp/run-python/

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-run-python" '{"command":"deno","args":["run","-N","-R=node_modules","-W=node_modules","--node-modules-dir=auto","jsr:@pydantic/mcp-run-python","stdio"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mcp-run-python": {
            "command": "deno",
            "args": [
                "run",
                "-N",
                "-R=node_modules",
                "-W=node_modules",
                "--node-modules-dir=auto",
                "jsr:@pydantic/mcp-run-python",
                "stdio"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-run-python": {
            "command": "deno",
            "args": [
                "run",
                "-N",
                "-R=node_modules",
                "-W=node_modules",
                "--node-modules-dir=auto",
                "jsr:@pydantic/mcp-run-python",
                "stdio"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect