Code execution · MCP server
MCP server code runner: MCP server, setup and security
MCP server code runner is an open-source MCP server that lets an AI agent execute code written in a variety of programming languages. Its repository has 242 stars and its last commit is from February 5, 2026 and it is licensed under MIT.
| Adoption (stars) | 24/40 | |
|---|---|---|
| Maintenance | 10/30 | |
| Framework (licence, registry, official) | 15/30 |
What MCP server code runner does
According to its repository: “Code Runner MCP Server which can run code in various programming languages.”
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. MCP server code runner is listed under Code execution, a category of 32 servers in the directory, where it ranks #9 by stars.
Installing and connecting MCP server code runner
Distribution modes declared in the official MCP registry:
- npm package (Node.js, usually started with
npx) - Docker (OCI) image
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 MCP server code runner:
- 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.
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 March 19, 2025, the formulahendry/mcp-server-code-runner repository has 242 stars and 35 forks, with 8 open issues. It has more stars than 80% of the servers in the directory. Last change 9 months ago. Version published in the registry: 0.1.9 (September 25, 2025).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
MCP server code runner is still a modest project: read its code and compare it with the alternatives before using it.
Strengths
- Widely followed: 242 stars
- Listed in the official MCP registry
- Permissive licence (MIT)
Limitations
- No commit for 9 months
Avoid if…
- You cannot isolate the agent (sandbox, container)
Alternatives
- Container use4.1K ★
- LLM Sandbox1.1K ★
- Tidewave Phoenix858 ★
- Superserve466 ★
- OrcaReplay281 ★
- Mailtrap66 ★
Learn more
Frequently asked questions
How do I install MCP server code runner?
MCP server code runner is distributed as npm package (Node.js, usually started with npx) and Docker (OCI) image. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of formulahendry/mcp-server-code-runner.
Is MCP server code runner free?
The code is published under the MIT licence and can be used free of charge.
Is MCP server code runner safe?
Points to watch: system access. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by formulahendry on GitHub. Check who maintains it before giving it access.
What are the alternatives to MCP server code runner?
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