mcp-sandbox
Execute scientific scripts (R, Python, GMT, LaTeX, Octave, Julia, etc.) in isolated, disposable containers with no host filesystem access.
README
<!-- SPDX-FileCopyrightText: 2026 Peter Lemenkov lemenkov@gmail.com SPDX-License-Identifier: Apache-2.0 -->
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 |
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.