ipybox
Verified Safeby gradion-ai
Overview
A lightweight and secure Python code execution sandbox for AI agents to perform data analysis or execute code actions within Docker containers.
Installation
uvx ipybox mcpEnvironment Variables
- DOCKER_HOST
Security Notes
The project is designed with security in mind, utilizing Docker containers for isolation, path validation to restrict host filesystem access, and a configurable firewall to limit network egress. It generally runs containers as a non-root user, which is a good security practice. However, as a code execution sandbox, its security is inherently tied to the robustness of Docker's isolation and the firewall implementation; a vulnerability in these underlying components could potentially lead to a container escape. Code generation for MCP clients occurs within the container, not on the host, mitigating risks there.
Similar Servers
mcp-server-code-execution-mode
This server enables LLM agents to execute Python code in a highly secure, isolated container environment, facilitating complex multi-tool orchestration and data analysis with minimal LLM context token usage.
mcp_massive
An AI agent orchestration server, likely interacting with LLMs and managing multi-agent workflows.
mcp-run-python
Execute Python code in a secure, sandboxed environment, often for AI agents or untrusted code execution.
AgentUp
AgentUp is an infrastructure framework for developing, deploying, and managing production-ready AI agents, providing Docker-like consistency, security, and extensibility.