hyperbox-mcp is an open-source MCP server that executes LLM-generated code inside disposable Docker or Podman containers. It provides an isolated execution layer for developers building AI agents or coding workflows that need to protect real projects and host environments.
In the AI security & guardrails space, hyperbox-mcp takes a focused approach. It focuses on running LLM-generated code without exposing a real project or host environment to unsafe changes. hyperbox-mcp is an open-source project aimed at developers building MCP clients and AI coding agents. The project is open source (MIT). It runs on the command line and API, and it can be self-hosted.
It is developed by Sanjay7089, and it first shipped in 2026. The project is developed in the open on GitHub with 55 commits in the last 90 days. Among its 6 catalogued features are MCP server, docker containers, and podman containers. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do