Node Code Sandbox MCP Server

@mozicim

代码仓库主页

基本信息

分类

推理

传输方式

stdio

作者

mozicim

关于 Node Code Sandbox MCP Server

# 🐢🚀 Node.js Sandbox MCP ServerThis repository hosts a Node.js server that implements the Model Context Protocol (MCP) for running JavaScript in isolated Docker containers. It allows for on-the-fly npm dependency installation, making it easy to execute code safely and efficient

#javascript #typescript#sandboxing#code-execution#code-sandbox#npm-dependencies#ai-agent #llm-tools #mcp-server #coding-agent #model-control-protocol

Node Code Sandbox MCP Server 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块，请前往代码仓库查看安装说明。

代码仓库

Node Code Sandbox MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Node Code Sandbox MCP?

Node Code Sandbox MCP provides a secure JavaScript execution environment tailored for AI applications. It allows coding agents and large language models (LLMs) to run JavaScript dynamically, install NPM packages, and retrieve results, all while adhering to the Model Control Protocol (MCP).

How to use Node Code Sandbox MCP?

Clone the repository, run npm install and npm start to start the server. Open http://localhost:3000 in a browser, input JavaScript code, and click "Run" to execute it. Alternatively, use the /execute and /install API endpoints. Packages can be installed via the interface command npm install <package-name> or the /install endpoint.

Key features of Node Code Sandbox MCP

Dynamic JavaScript execution in a secure sandbox
NPM package installation and usage on demand
MCP compatibility for seamless AI agent integration
Sandboxing prevents unauthorized access and ensures safety
Interactive code generation and testing via web interface

Use cases of Node Code Sandbox MCP

Code generation and validation for LLM-based coding assistants
Dynamic script execution in AI-driven development workflows
Safe testing and prototyping of JavaScript snippets with dependencies
Interactive assistance where LLMs need to run and inspect JS code

常见问题

What are the prerequisites for using Node Code Sandbox MCP?

Node.js (version 14 or higher), NPM, and basic knowledge of JavaScript and AI concepts are required.

How can I install and start the server?

Clone the repository, navigate to the project directory, run `npm install`, then `npm start`. The server runs on `http://localhost:3000`.

What API endpoints are available?

The server provides a POST `/execute` endpoint to run code (with a `code` field) and a POST `/install` endpoint to install NPM packages (with a `package` field).

Does Node Code Sandbox MCP support NPM packages?

Yes. You can install packages using the `npm install <package-name>` command in the web interface or via the `/install` API endpoint.

How does sandboxing protect the host environment?

Sandboxing ensures secure execution to prevent unauthorized access and system compromise during code runs.

推理分类下的更多 MCP 服务器

quarkus-langchain4j-workshop

quarkusio

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

MCP Sandbox

JohanLi233

Python sandboxes for llms

Agentic Radar

splx-ai

A security scanner for your LLM agentic workflows

993

AWorld: Advancing Agentic AI

inclusionAI

Search, understand, reproduce, and improve an idea with ease

1.2K

Part 1. Real-Time LangGraph Agent with MCP Tool Execution

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