# Python Exec Sandbox

> Use this tool when you need to execute Python code in a secure and isolated environment, allowing AI agents to run multiple versions of Python with inline dependencies and zero pollution. It solves problems of code security, dependency management, and version compatibility, providing a reliable interface for inputting code and receiving output. Ideal for use cases requiring sandboxed execution, such as testing, validation, and deployment of Python-based AI models.

Canonical page: https://skillsregistry.net/skills/io-github-lu-zhengda-mcp-python-exec-sandbox  
JSON: https://api.skillsregistry.net/v1/skills/io-github-lu-zhengda-mcp-python-exec-sandbox

## Description

Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 0.1.5
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.lu-zhengda%2Fmcp-python-exec-sandbox)
- **Repository:** <https://github.com/lu-zhengda/mcp-python-exec-sandbox>

## 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": "io-github-lu-zhengda-mcp-python-exec-sandbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-lu-zhengda-mcp-python-exec-sandbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-lu-zhengda-mcp-python-exec-sandbox/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