Skip to main content
Glama
lemenkov

mcp-sandbox

by lemenkov

mcp-sandbox

MCP server for isolated scientific script execution. Run R, Python, GMT, LaTeX, Octave, Julia, and more in disposable containers — fully stateless, no host filesystem access.

Tools

Tool

Description

run_script

Execute a script in an isolated sandbox container

list_runtimes

List available scientific runtimes

Related MCP server: Node.js Sandbox MCP Server

Supported Runtimes

Runtime

Tools

r

R + ggplot2, dplyr, tidyr, jsonlite

python

Python 3 + numpy, matplotlib, scipy, pandas, sympy, scikit-learn

gmt

Generic Mapping Tools

latex

pdflatex (texlive)

octave

GNU Octave

julia

Julia

gnuplot

Gnuplot

bash

Bash scripts

Design

  • Each run spawns a fresh container — fully stateless, no reuse

  • Container deleted after execution (--rm)

  • Network access enabled

  • Memory limit: 2GB, CPU limit: 2 cores

  • Input files injected at /sandbox/input/ (base64)

  • Output files collected from /sandbox/output/ (base64)

Build the sandbox image

podman build -t mcp-sandbox:latest -f Containerfile .

Install

useradd -r -m -d /var/lib/mcp-sandbox sandbox
echo "sandbox:100000:65536" >> /etc/subuid
echo "sandbox:100000:65536" >> /etc/subgid

python3 -m venv venv
venv/bin/pip install -e .

Configuration

HOST=127.0.0.1
PORT=8815
SANDBOX_IMAGE=mcp-sandbox:latest
DEFAULT_TIMEOUT=60
MAX_TIMEOUT=300

License

Apache-2.0

A
license - permissive license
-
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lemenkov/mcp-sandbox'

If you have feedback or need assistance with the MCP directory API, please join our Discord server