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.
@alfonsograziano
基本情報
A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"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"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
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.
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.
Docker must be installed and running on your machine. Pre‑pulling images like `node:lts-slim` is recommended to avoid delays.
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.
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.
Set environment variables `SANDBOX_MEMORY_LIMIT` (e.g., `512m`) and `SANDBOX_CPU_LIMIT` (e.g., `0.5`) when launching the server.
Yes. The `image` parameter in tools like `run_js_ephemeral` and `sandbox_initialize` accepts any Docker image (default is `node:lts-slim`).
A Model Context Protocol (MCP) server that enables LLMs to run ANY code safely in isolated Docker containers.
Python sandboxes for llms
This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.
Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.
An MCP server that allows you to run TypeScript, JavaScript, and Python code in a sandbox on your local machine using the Deno® sandbox. This server provides a controlled environment for executing code with explicit permission controls.
コメント