ipybox
Verified Safeby 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
uvx ipybox --workspace /path/to/workspaceEnvironment 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
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.
Lynkr
Lynkr is an AI orchestration layer that acts as an LLM gateway, routing language model requests to various providers (Ollama, Databricks, OpenAI, etc.). It provides an OpenAI-compatible API and enables AI-driven coding tasks via a rich set of tools and a multi-agent framework, with a strong focus on security, performance, and token efficiency. It allows AI agents to interact with a defined workspace (reading/writing files, executing shell commands, performing Git operations) and leverages long-term memory and agent learning to enhance task execution.
mcp_massive
An AI agent orchestration server, likely interacting with LLMs and managing multi-agent workflows.
mcp-run-python
MCP server to securely run untrusted Python code in a sandboxed WebAssembly environment, typically as a tool for AI agents.