# ipybox

> ipybox

Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.

ipybox executes code blocks in a stateful IPython kernel. A code block can contain any
combination of Python code, shell commands, and programmatic MCP tool calls. Kernels can be
sandboxed with sandbox-runtime, enforcing filesystem and network restrictions at OS level.

It generates Python APIs for MCP server tools via mcpygen, and supports application-level
approval of individual tool calls and shell commands during code execution. ipybox runs
locally on your computer, enabling protected access to your local data and tools.


## Documentation

- [Overview](https://gradion-ai.github.io/ipybox/index.md): Project overview and capabilities
- [Installation](https://gradion-ai.github.io/ipybox/installation/index.md): Installation and setup instructions
- [Quickstart](https://gradion-ai.github.io/ipybox/quickstart/index.md): Getting started guide
- [Architecture](https://gradion-ai.github.io/ipybox/architecture/index.md): Architecture overview
- [API generation](https://gradion-ai.github.io/ipybox/apigen/index.md): Generating typed Python API from MCP server schemas
- [Code execution](https://gradion-ai.github.io/ipybox/codeexec/index.md): Code and shell command execution in IPython kernels
- [Sandboxing](https://gradion-ai.github.io/ipybox/sandbox/index.md): Lightweight sandboxing with Anthropic's sandbox-runtime
- [ipybox MCP Server](https://gradion-ai.github.io/ipybox/mcpserver/index.md): Using ipybox as an MCP server
- [Claude Code plugin](https://gradion-ai.github.io/ipybox/ccplugin/index.md): a plugin for programmatic tool calling in Claude Code

## API Reference

- [Code Executor](https://gradion-ai.github.io/ipybox/api/code_executor/index.md): CodeExecutor high-level API
- [Kernel Manager](https://gradion-ai.github.io/ipybox/api/kernel_manager/index.md): KernelGateway and KernelClient low-level API