LabscoMCP early access ↗
TsuchijoMCP SERVER

Sandbox MCP Server

Isolated Docker containers a model can create, write code into, and run — then save as an image.

by Tsuchijo ↗Sandboxed Code ExecutionCommunity

LABSCO SUMMARY

Code runs somewhere it cannot damage anything, and the environment survives if you want it.

The isolation is the obvious part; the reproducibility is the useful part. Being able to install packages interactively, then commit the result as an image or export a Dockerfile, means an exploratory session ends with something you can hand to someone else instead of a transcript of installs.

What it is

An MCP server that gives a model disposable Docker environments. It can start a container from any image, write files into it, run commands, and — when the environment is worth keeping — commit it or export a Dockerfile that recreates it.

What you get

  • create_container_environment — a new container from the image you name
  • create_file_in_container — write a file inside it
  • execute_command_in_container — run commands in the isolated container
  • save_container_state — commit the container, with its installed packages and files, as a persistent Docker image
  • export_dockerfile — emit a Dockerfile that rebuilds the environment, with the base image and created files
  • exit_container — close a container and clean up
  • Containers can be made persistent so they survive the client closing and stay reachable through docker exec

Requirements

Python 3.9 or higher, Docker installed and running, and the uv package manager. Clone the repo, create the environment with uv venv, install with uv pip install ., then register the uv --directory <YOUR_PATH_TO_SANDBOX_MCP> run sandbox_server.py command in claude_desktop_config.json with PYTHONPATH pointing at the same directory. Package version 0.1.0.

Setup effort

Build from source — git clone https://github.com/Tsuchijo/sandbox-mcp.git

See installation options