Node.js Sandbox MCP Server

@alfonsograziano

Basic information

About Node.js Sandbox MCP Server

A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.

#node-js #javascript #typescript #docker

Node.js Sandbox MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "js-sandbox": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/var/run/docker.sock:/var/run/docker.sock",
        "-v",
        "$HOME/Desktop/sandbox-output:/root",
        "-e",
        "FILES_DIR=$HOME/Desktop/sandbox-output",
        "alfonsograziano/node-code-sandbox-mcp"
      ]
    }
  }
}

Node.js Sandbox MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is 🐢🚀 Node.js Sandbox MCP Server?

It is a Node.js server implementing the Model Context Protocol (MCP) for running arbitrary JavaScript in ephemeral Docker containers with on‑the‑fly npm dependency installation. It is for developers and AI agents who need an isolated, sandboxed JavaScript execution environment.

How to use 🐢🚀 Node.js Sandbox MCP Server?

Install and run via Docker or npx, then configure your MCP client (e.g., Claude Desktop, VS Code) with the provided JSON config. Pass environment variables like FILES_DIR, SANDBOX_MEMORY_LIMIT, and SANDBOX_CPU_LIMIT. Use tools such as run_js_ephemeral for one‑off scripts or sandbox_initialize → run_js → sandbox_stop for session‑based workflows.

Key features of 🐢🚀 Node.js Sandbox MCP Server

Isolated Docker containers for each sandbox.
Execute shell commands inside running containers.
Install specified npm packages per job.
Run ES module JavaScript snippets and capture stdout.
Clean teardown of containers after use.
Detached mode for long‑running servers (background processes).

Use cases of 🐢🚀 Node.js Sandbox MCP Server

Quick one‑off JavaScript experiments with automatic cleanup.
Run multi‑step scripts in a persistent sandbox environment.
Spin up temporary servers with exposed ports for testing.
Search npm packages and test them in isolation.
Generate files (e.g., QR codes, images) and retrieve them automatically.

Frequently asked questions

What are the prerequisites?

Docker must be installed and running on your machine. Pre‑pulling images like `node:lts-slim` is recommended to avoid delays.

How do I get files back from a script?

Save files during script execution in the container’s working directory. Images (PNG, JPEG) are returned as image content; other files (e.g., .txt, .json) are returned as resource content. This feature is available only in the `run_js_ephemeral` tool.

What is detached mode?

Detached mode keeps the container alive after script execution, allowing long‑running services (e.g., servers) to stay active in the background. Use `run_js` with the `listenOnPort` parameter.

How can I limit container resources?

Set environment variables `SANDBOX_MEMORY_LIMIT` (e.g., `512m`) and `SANDBOX_CPU_LIMIT` (e.g., `0.5`) when launching the server.

Can I use custom Docker images?

Yes. The `image` parameter in tools like `run_js_ephemeral` and `sandbox_initialize` accepts any Docker image (default is `node:lts-slim`).

Comments

More Reasoning MCP servers

quarkus-langchain4j-workshop

quarkusio

Quarkus LangChain4J Workshop that demonstrates both single AI service capabilities and Agentic AI orchestration

MCP Servers

junfanz1

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent

n8n Workflow Builder MCP

ifmelate

MCP server that allow LLM in agent mode builds n8n workflows for you

Agentic Swmm Workflow

Zhonghao1995

Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex,

mcp-agentic-rag

rukshannet

MCP Server for Agentic RAG applications