# Python Sandbox

> Use this tool when you need to execute Python code in a safe and controlled environment, such as for interactive code examples or educational purposes. It solves problems of dependency management and security by providing a sandboxed environment with automatic package installation and standardized output. The tool accepts Python code snippets as input and returns execution results in a structured XML format, making it ideal for use in browser-compatible applications and AI assistants.

Canonical page: https://skillsregistry.net/skills/pydantic-run-python  
JSON: https://api.skillsregistry.net/v1/skills/pydantic-run-python

## Description

MCP-Run-Python provides a sandboxed environment for executing Python code through a standardized interface. Built with TypeScript and Pyodide, it allows AI assistants to run Python snippets safely in a browser-compatible environment, supporting package installation through PEP 723 script metadata. The server offers both SSE and stdio transport options, handles dependency management automatically, and returns execution results in a structured XML format containing stdout, stderr, and return values. This implementation is particularly valuable for interactive code examples, educational tools, and AI assistants that need to demonstrate or test Python code without requiring a full backend Python environment.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/pydantic-run-python)
- **Repository:** <https://github.com/pydantic/pydantic-ai/tree/HEAD/mcp-run-python>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "pydantic-run-python"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pydantic-run-python` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pydantic-run-python/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt