Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
MCPpedia last refreshed this data
io.github.vndee/llm-sandbox is an MCP server that securely run LLM-generated code in isolated containers across 7 languages and 3 container backends. Its tool list has not been published yet over stdio and http, requires no API key, and scores 86/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients - only the file and path differ.
{
"mcpServers": {
"llm-sandbox": {
"args": [
"-m",
"llm_sandbox.mcp_server.server"
],
"command": "python3"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
This server supports HTTP transport. Be the first to test it - help the community know if it works.
Five weighted categories - click any category to see the underlying evidence.
No known CVEs.
Checked llm-sandbox against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience - it helps other developers decide.
Sign in to write a review.
Others in developer-tools
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Manage Supabase projects — databases, auth, storage, and edge functions
MCP server for using the GitLab API
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
MCP Security Weekly
Get CVE alerts and security updates for io.github.vndee/llm-sandbox and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Securely Execute LLM-Generated Code with Ease
LLM Sandbox runs Large Language Model (LLM) generated code through a common API for container and local Linux and Windows sandbox backends. Choose an isolation backend for your deployment, configure its security controls, and reuse the same code execution and file APIs.
Documentation: https://vndee.github.io/llm-sandbox/
Backend benchmarks compare Docker, Bubblewrap and NsJail across startup, execution, file transfers and concurrency, with confidence intervals and reproducible evidence.

✨ 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.
Execute code in multiple programming languages with automatic dependency management:
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/.