# QuickJS Sandbox

> Use this tool when you need to execute arbitrary JavaScript code in a secure and isolated environment, capturing output and errors without risking the host system. It solves problems of code testing and demonstration for language models, providing a safe sandbox for untrusted code. The tool takes JavaScript code as input and returns stdout, stderr, and execution errors as output.

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

## Description

An MCP server that provides a secure JavaScript execution environment using QuickJS compiled to WebAssembly. It exposes a single tool, 'run_javascript_code', which executes arbitrary JavaScript code within a sandboxed WASM environment, capturing stdout, stderr, and execution errors. The implementation uses Node.js's built-in WASI module and temporary files to safely isolate potentially untrusted code from the host system, making it ideal for language models that need to test or demonstrate JavaScript code without security risks.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/quickjs-sandbox)
- **Repository:** <https://github.com/jlucaso1/mcp-javascript-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": "quickjs-sandbox"
    }
  }
}
```

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