LLM Sandbox MCP server
io.github.vndee/llm-sandbox·v0.3.43·1.1k starsSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
1.1k stars113k downloads/wk
Reviews
Write oneNobody has reviewed LLM Sandbox yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
LLM Sandbox tools (3, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
execute_codewrite actionExecute code in a secure sandbox environment and automatic visualization capture.
get_language_detailsGet the details of a language.
get_supported_languagesGet the list of supported languages.
Public scan report
scanner v0.1.10 · 2026-11-05 · same rubric, same numbers if you re-run it
- Code scan49 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How LLM Sandbox compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 90% of 4,456 AI and agents servers
- Tools
- 3
- the typical AI and agents server has 7
- Tools that change things
- 33%
- typical: 3%. Fewer write tools means less an agent can break
- GitHub stars
- 1,143
- more than 95% of 2,733 AI and agents servers
- Downloads a week
- 113,139
- more than 96% of 1,712 AI and agents servers with a package
What its tools let an agent do: 2 read · 1 run or deploy
Install LLM Sandbox in Claude Code, Cursor or VS Code
claude mcp add llm-sandbox -- uvx llm-sandbox
What the publisher says
From the LLM Sandbox repository's README, as published. We do not edit it. Read it on GitHub
<!-- mcp-name: io.github.vndee/llm-sandbox -->
LLM Sandbox
Securely Execute LLM-Generated Code with Ease
LLM Sandbox is a lightweight and portable sandbox environment designed to run Large Language Model (LLM) generated code in a safe and isolated mode. It provides a secure execution environment for AI-generated code while offering flexibility in container backends and comprehensive language support, simplifying the process of running code generated by LLMs.
Documentation: https://vndee.github.io/llm-sandbox/
✨ New: This project now supports the Model Context Protocol (MCP) server, which allows your MCP clients (e.g. Claude Desktop) to run code generated by LLMs in a secure sandbox environment.
🚀 Key Features
🛡️ Security First
- Isolated Execution: Code runs in isolated containers with no access to host system
- Security Policies: Define custom security policies to control code execution
- Resource Limits: Set CPU, memory, and execution time limits
- Network Isolation: Control network access for sandboxed code
🏗️ Flexible Container Backends
- Docker: Most popular and widely supported option
- Kubernetes: Enterprise-grade orchestration for scalable deployments
- Podman: Rootless containers for enhanced security
🌐 Multi-Language Support
Execute code in multiple programming languages with automatic dependency management:
- Python - Full ecosystem support with pip packages
- JavaScript/Node.js - npm package installation
- Java - Maven and Gradle dependency management
- C++ - Compilation and execution
- Go - Module support and compilation
- R - Statistical computing and data analysis with CRAN packages
🔌 LLM Framework Integration
Runnable examples for eleven agent frameworks — OpenAI Agents SDK, Claude Agent SDK, LangChain, DeepAgents, LlamaIndex, Google ADK, CrewAI, Pydantic AI, smolagents, Strands and AG2. See examples/agent_sdks/.
📊 Advanced Features
- Artifact Extraction: Automatically capture plots and visualizations
- Library Management: Install dependencies on-the-fly
- File Operations: Copy files to/from sandbox environments
- Custom Images: Use your own container images
- Fast Production Mode: Skip environment setup for faster container startup
- Container Pooling: Pre-warm and reuse containers for improved performance (NEW!)
📦 Installation
Basic Installation
pip install llm-sandboxWith Specific Backend Support
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
LLM Sandbox: common questions
- Is LLM Sandbox MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the LLM Sandbox safety report
- How do I install LLM Sandbox?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does LLM Sandbox need an API key?
- No secret keys are declared. It reads 12 settings from the environment.
- Is LLM Sandbox maintained?
- The last commit was 11 days ago (2026-11-05). The latest release is v0.3.43.
- What can I use instead of LLM Sandbox?
- Servers from other publishers that do the same job: Butterbase AI MCP server, Grandet MCP server and Decionis Commerce Gate MCP server.
- How does LLM Sandbox compare with other AI and agents MCP servers?
- safety score 92/100 (higher than 90% of 4,456 AI and agents servers); tools 3 (the typical AI and agents server has 7); tools that change things 33% (typical: 3%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to LLM Sandbox
Same job from other publishers: the closest match first, then the best rated.
- Butterbase AIButterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys.not reviewedEstablishedA
- GrandetCheapest API for any model across official, inference and relay providers; find free creditsnot reviewedEstablishedA
Decionis Commerce Gate MCPCommerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors.not reviewedEstablishedC- SkillsmithShare agent skills across your team, scan them for risk, and track what's actually used.not reviewedEstablishedB
