SecBear/nix-sandbox-mcp
Sandboxed code execution for LLMs, powered by Nix
This project helps developers give Large Language Models (LLMs) the ability to run code safely and reliably. It provides sandboxed environments (like Python, Node.js, or shell) where the LLM can execute code, take project files as input, and produce output without affecting the host system. It's used by developers building LLM applications who need robust, isolated code execution capabilities.
Use this if you need to let an LLM run code in a secure, isolated, and reproducible environment, especially when using self-hosted LLM clients.
Not ideal if you need to run LLM code execution on macOS or Windows, or if you require full VM-level isolation for highly untrusted code without Linux.
Stars
12
Forks
1
Language
Rust
License
MIT
Category
Last pushed
Feb 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/SecBear/nix-sandbox-mcp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dust-tt/dust
Custom AI agent platform to speed up your work.
winfunc/deepreasoning
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning...
imfing/jsrun
Modern JavaScript runtime in Python, powered by V8 and bridged by Rust
opencrust-org/opencrust
Personal AI assistant platform, rewritten in Rust from OpenClaw
puremachinery/carapace
A secure, stable Rust alternative to openclaw/moltbot/clawdbot