MCP Sandbox: Your JavaScript Module in a Secure Environment

Name: MCP Sandbox: Your JavaScript Module in a Secure Environment
Author: TrHung1910

@TrHung1910

代码仓库

基本信息

分类

推理

许可证

MIT license

传输方式

stdio

作者

TrHung1910

关于 MCP Sandbox: Your JavaScript Module in a Secure Environment

MCP Sandbox transforms JavaScript modules into secure MCP servers, enabling AI systems to access functions safely. With automatic reflection and type inference, it simplifies the integration process for developers. 🛠️💻

#python #go #docker #playground #automation #reflection #typescript #ai#sandboxing#server-sent-events #agents #code-execution #uv#code-sandbox#npm-dependencies#security-sandbox#llm-tools #model-context-protocol

MCP Sandbox: Your JavaScript Module in a Secure Environment 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

MCP Sandbox: Your JavaScript Module in a Secure Environment 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 MCP Sandbox?

MCP Sandbox is a tool that converts any JavaScript module into a sandboxed Model Context Protocol (MCP) server, providing automatic reflection, type inference, and secure execution. It is designed for developers who need a safe, efficient environment to run JavaScript modules within the MCP framework.

How to use MCP Sandbox?

Clone the repository, install dependencies with npm install, and run npm start. Alternatively, download a release from the Releases section. Create a JavaScript module (e.g., myModule.js), then use createSandbox('myModule.js') to wrap it, set up a message event listener, and call sandbox.run(). Interact with the module by sending and receiving messages in real time.

Key features of MCP Sandbox

Sandboxed execution of JavaScript modules.
Automatic reflection for dynamic property/method access.

推理分类下的更多 MCP 服务器

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

Agentic Radar

splx-ai

A security scanner for your LLM agentic workflows

993

MCP Sandbox

JohanLi233

Python sandboxes for llms

AWorld: Advancing Agentic AI

inclusionAI

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

1.2K

Agentic MCP Client

peakmojo

A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.