ipybox

Provides secure Python code execution in Docker containers with stateful IPython kernels, real-time output streaming, file operati

gradion-ai 73
Claude CodeClaude DesktopGeneric
View source ↗

ipybox provides secure Python code execution in Docker containers with stateful IPython kernels, built by Gradion AI for AI agents that need safe code execution environments. The implementation combines Docker isolation with dual-server architecture: Jupyter Kernel Gateway manages IPython kernels for persistent code execution while a FastAPI resource server handles file operations, module introspection, and MCP tool integration through auto-generated Python client functions. Features include configurable network firewalls restricting outbound traffic to whitelisted domains, real-time output streaming with image support, bidirectional file transfers, and seamless integration of both local (stdio) and remote (HTTP/SSE) MCP servers, making it valuable for data analytics workflows, automated testing, and AI agent code actions that require isolated execution environments.

Source

Repository: https://github.com/gradion-ai/ipybox

Maintain ipybox?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[ipybox on getagentictools](https://getagentictools.com/mcp/gradion-ai-ipybox?ref=badge)