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:

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.

Release files for ipybox 0.9.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ipybox 0.9.2
File	Size	Uploaded
ipybox-0.9.2.tar.gz	21.9 kB	Jun 1, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for ipybox 0.9.2
File	Interpreter	ABI	Platform	Reset
ipybox-0.9.2-py3-none-any.whl 26.3 kB Jun 1, 2026	Python 3	none	any	Details

Total release size: 48.2 kB

Release files / ipybox-0.9.2.tar.gz

Download URL	ipybox-0.9.2.tar.gz
Size	21.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`44e67671a87c12b85355027b248767044e9b5d2e2994d4c41af8a18e79649dff`
BLAKE2b-256 checksum How to use checksums	`d340cfe42d6b2ace722d85e0d462d7584a458daf67ad0fb90fd53539cf079e99`
Upload date	Jun 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/gradion-ai/ipybox
Publishing commit: github.com/gradion-ai/ipybox/tree/9b74ee4dbbe0e9295e3053f72734f3af0a2430ea

Workflow

Publishing configuration: github.com/gradion-ai/ipybox/blob/9b74ee4dbbe0e9295e3053f72734f3af0a2430ea/.github/workflows/release.yml
Publishing logs: github.com/gradion-ai/ipybox/actions/runs/26747990594/attempts/1

Artifact

Subject: ipybox-0.9.2.tar.gz
SHA-256 checksum: 44e67671a87c12b85355027b248767044e9b5d2e2994d4c41af8a18e79649dff Verifying attestations

Release files / ipybox-0.9.2-py3-none-any.whl

Download URL	ipybox-0.9.2-py3-none-any.whl
Size	26.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`3e8f0e71860b6b4a5dbd901c697441d621cee3d366f5526ad48850505dd896b0`
BLAKE2b-256 checksum How to use checksums	`06f001d21ec61067541b49adadbf20787ff257a6b4731cb8f629d480e62742c6`
Upload date	Jun 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/gradion-ai/ipybox
Publishing commit: github.com/gradion-ai/ipybox/tree/9b74ee4dbbe0e9295e3053f72734f3af0a2430ea

Workflow

Publishing configuration: github.com/gradion-ai/ipybox/blob/9b74ee4dbbe0e9295e3053f72734f3af0a2430ea/.github/workflows/release.yml
Publishing logs: github.com/gradion-ai/ipybox/actions/runs/26747990594/attempts/1

Artifact

Subject: ipybox-0.9.2-py3-none-any.whl
SHA-256 checksum: 3e8f0e71860b6b4a5dbd901c697441d621cee3d366f5526ad48850505dd896b0 Verifying attestations