execute_codeLABSCO SUMMARY
One tool, and the language is an argument.
The surface is deliberately tiny — a single call where the language is just a string — which means no per-language tool clutter in the context and no local toolchain to install for Rust, Swift or Scala. The cost model follows: you are handing execution to a hosted service under an API token, so treat the code you send as leaving the machine.
What it is
An MCP server in front of NetMind's hosted code execution service. The assistant sends source files and gets execution results back; the container is isolated, resource-limited and thrown away afterwards, so nothing runs on your machine.
What you get
execute_code— pick a language, pass a list of files each with a name and full contents, and optionally stdin and command-line arguments- Language identifiers covering python, javascript, typescript, java, cpp, c, go, rust, php, ruby, swift, kotlin, scala and r
- Multi-file programs, not just snippets — you send the whole set and it runs them together
- Results as stdout, stderr and data outputs on success, or an error description on failure
- Plots and charts your code writes are captured and returned as a link, with no extra step
- A sandboxed filesystem the program can read from and write to during the run
Requirements
A NetMind API key, set as NETMIND_API_TOKEN. The documented client config runs it with uvx, so you need uv installed — via Homebrew or the install script. Nothing else is needed locally: execution happens on NetMind's infrastructure. MIT licensed.
Setup effort
Follow the published steps — uvx --from git+https://github.com/protagolabs/Netmind-Code-Interpreter-Mcp netmind-code-interpreter
USE CASES
01
Checking that generated code actually runs
Have the assistant execute what it just wrote and read the real stderr instead of assuming it compiles.
02
Trying a language you have not installed
Run the Rust or Swift snippet by naming the language — no toolchain, no container of your own.
03
Turning data into a chart in the conversation
Let the program write a plot; the image comes back as a link with the run output.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
NETMIND_API_TOKEN in your environment
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx --from git+https://github.com/protagolabs/Netmind-Code-Interpreter-Mcp netmind-code-interpreterConfigure your MCP client to connect to http://localhost:8000/sse
