Code execution · MCP server
Node code sandbox MCP: MCP server, setup and security
Node code sandbox MCP is an MCP server published on GitHub that lets an AI agent run JavaScript in isolated Docker sandboxes with dynamic npm dependencies. Its repository has 158 stars and its last commit is from November 24, 2025, but it declares no licence.
What Node code sandbox MCP does
According to its repository: “Run JavaScript snippets in isolated Docker sandboxes with on-the-fly npm dependency installation and clean teardown.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Node code sandbox MCP is listed under Code execution, a category of 32 servers in the directory, where it ranks #12 by stars.
Installing and connecting Node code sandbox MCP
No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for Node code sandbox MCP:
- System access: the Code execution category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.
- No licence: without a licence the code is not legally reusable, even if it is public. Avoid it in a company setting without the author's agreement.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on April 26, 2025, the alfonsograziano/node-code-sandbox-mcp repository has 158 stars and 35 forks, with 10 open issues. It has more stars than 74% of the servers in the directory. Last change 11 months ago.
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Node code sandbox MCP is still a modest project: read its code and compare it with the alternatives before using it.
Limitations
- No commit for 11 months
- No licence declared
- Install from source
Avoid if…
- You cannot isolate the agent (sandbox, container)
- Company use without the author's agreement
Alternatives
- Container use4.1K ★
- LLM Sandbox1.1K ★
- Tidewave Phoenix858 ★
- Superserve466 ★
- OrcaReplay281 ★
- Mailtrap66 ★
Learn more
Frequently asked questions
How do I install Node code sandbox MCP?
No package is declared in the MCP registry: clone the alfonsograziano/node-code-sandbox-mcp repository, follow its README, then declare the start command in your client's MCP configuration.
Is Node code sandbox MCP free?
The code is public but has no declared licence: it is not formally free to reuse.
Is Node code sandbox MCP safe?
Points to watch: system access and no licence. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by alfonsograziano on GitHub. Check who maintains it before giving it access.
What are the alternatives to Node code sandbox MCP?
In the same category: Container use, LLM Sandbox, Tidewave Phoenix, and Superserve. Container use and LLM Sandbox score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score