# JavaScript Sandbox

> Use this tool when you need to execute JavaScript code in a secure and isolated environment, solving problems like code testing, algorithm evaluation, and providing a safe playground for AI models. It takes in JavaScript code as input and outputs the execution results, with configurable time and memory limits to prevent resource exhaustion. Ideal for use cases where security and resource control are crucial, such as testing untrusted code or training AI models to interact with JavaScript.

Canonical page: https://skillsregistry.net/skills/garc33-js-sandbox  
JSON: https://api.skillsregistry.net/v1/skills/garc33-js-sandbox

## Description

This JavaScript sandbox MCP server, developed by an unknown author, provides a secure environment for executing JavaScript code within defined constraints. Built with TypeScript and leveraging the Model Context Protocol SDK, it offers a tool for running arbitrary JavaScript with configurable time and memory limits. The implementation focuses on isolation and security, utilizing the vm2 library to create a controlled execution context. It's particularly useful for tasks like code testing, algorithm evaluation, or providing a safe playground for AI models to experiment with JavaScript, enabling assistants to execute and analyze JavaScript code without risking system integrity or resource exhaustion.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/garc33-js-sandbox)
- **Repository:** <https://github.com/garc33/js-sandbox-mcp-server>

## 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": "garc33-js-sandbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/garc33-js-sandbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/garc33-js-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