# mcp-sandbox

> Use this tool when you need to execute scientific scripts in a secure and isolated environment, solving problems related to data privacy and script compatibility. It takes in scripts written in various languages, such as R, Python, and Julia, and outputs the results of the execution, providing a safe and reliable way to run untrusted or untested code. Ideal for use cases where host filesystem access is a security concern, such as testing, validation, or collaboration.

Canonical page: https://skillsregistry.net/skills/lemenkov-mcp-sandbox  
JSON: https://api.skillsregistry.net/v1/skills/lemenkov-mcp-sandbox

## Description

Execute scientific scripts (R, Python, GMT, LaTeX, Octave, Julia, etc.) in isolated, disposable containers with no host filesystem access.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/mxmpak7wts)
- **Repository:** <https://github.com/lemenkov/mcp-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": "lemenkov-mcp-sandbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lemenkov-mcp-sandbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lemenkov-mcp-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