Back to Home
gradion-ai icon

ipybox

Verified Safe

by gradion-ai

Overview

A Python code execution sandbox for AI agents to programmatically interact with MCP tools and execute code actions in a stateful, sandboxed environment.

Installation

Run Command
uvx ipybox --workspace /path/to/workspace

Environment Variables

  • GITHUB_API_KEY
  • BRAVE_API_KEY
  • TOOL_SERVER_HOST
  • TOOL_SERVER_PORT
  • KERNEL_ENV_*

Security Notes

The server is explicitly designed to execute untrusted Python code. It provides strong mitigation through Anthropic's `sandbox-runtime` for kernel isolation (filesystem and network control) and mandates application-level approval for all MCP tool calls. However, `sandbox-runtime` currently has platform limitations (primarily macOS support), and running `ipybox` without sandboxing (an available option, though warned against) carries significant security risks, as it would execute arbitrary code directly on the host machine. Docker containerization is suggested for Linux/Windows to mitigate this.

Similar Servers

Stats

Interest Score45
Security Score8
Cost ClassHigh
Avg Tokens5000
Stars61
Forks16
Last Update2026-01-19

Tags

AI agentscode executionsandboxingMCP toolsPythonLLM integration