Summary
This is a code execution environment that runs Python, shell commands, and MCP tool calls in a single stateful IPython kernel. It generates typed Python APIs from MCP tool schemas using mcpygen, so tools are invoked as function calls rather than raw JSON. You get application-level approval for individual tool calls and shell commands during execution, plus optional sandboxing via Anthropic's sandbox-runtime for filesystem and network restrictions. Everything runs locally. Reach for this when you need an LLM to execute multi-step Python workflows that combine local scripts, system commands, and calls to other MCP tools, all while maintaining state across executions. The project also ships as a Claude Code plugin and includes Freeact, a general-purpose agent built on top of it.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
ipybox
mcp-name: io.github.gradion-ai/ipybox
ipybox is a unified execution environment for Python code, shell commands, and programmatic MCP tool calls.
Overview
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.
[!NOTE] Next generation ipybox
This is the next generation of ipybox, a complete rewrite. Older versions are maintained on the 0.6.x branch and can be obtained with
pip install ipybox<0.7.
Documentation:
- 📚 Documentation
- 🏗️ Architecture
- 🤖 llms.txt
- 🤖 llms-full.txt
Capabilities
| Capability | Description |
|---|---|
| Stateful execution | State persists across executions in IPython kernels |
| Unified execution | Combine Python code, shell commands, and programmatic MCP tool calls in a code block |
| Shell command execution | Run shell commands via !cmd syntax, capture output into Python variables |
| Programmatic MCP tool calls | MCP tools called via generated Python API ("code mode"), not JSON directly |
| Python tool API generation | Typed functions and Pydantic models generated from MCP tool schemas via mcpygen |
| Application-level approval | Individual approval of tool calls and shell commands during code execution |
| Lightweight sandboxing | Optional kernel isolation via Anthropic's sandbox-runtime |
| Local execution | No cloud dependencies, everything runs locally on your machine |
Usage
| Component | Description |
|---|---|
| Python SDK | Python API for building applications on ipybox |
| MCP server | ipybox as MCP server for code actions and programmatic tool calling |
| Claude Code plugin | Plugin that bundles the ipybox MCP server and a code action skill |
[!TIP] Freeact agent
Freeact is a general-purpose agent built on ipybox.
Featured
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
