1. Conduid
  2. Developer Tools
  3. ipybox
MCP server · Developer Tools

ipybox

by · github.com/gradion-ai/ipybox

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

Unclaimed Apache-2.0 devtoolscode-executioncode-sandboxclaude-code-plugincode-modemcp-clientipythonmcpcode-interpreter
InstallView source
77Good

Scored 3 days ago · breakdown

About ipybox

ipybox is an MCP server published by gradion-ai in the Developer Tools category: unified execution environment for Python code, shell commands, and programmatic MCP tool calls.

The repository has 76 stars and 19 forks, with the last commit 4 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/gradion-ai/ipybox

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about ipybox

Powered by Claude · Grounded in docs

I know everything about ipybox. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 4 days ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • !No dynamic code executionSource scan found eval or shell execution. Review how tool inputs reach it before granting credentials.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

0.9.20.9.2 · 1 Jun 2026What's Changed Make kernel-init timeout configurable (#55) by @krasserm in https://github.com/gradion-ai/ipybox/pull/56 Full Changelog: https://github.com/gradion-ai/ipybox/compare/0.9.1...0.9.2
0.9.10.9.1 · 24 Mar 2026What's Changed Add %%bash/%%sh cell magic approval support by @krasserm in https://github.com/gradion-ai/ipybox/pull/52 Use shell_magic tool_name for %%bash/%%sh approval requests by @krasserm in…
0.9.00.9.0 · 21 Mar 2026What's Changed Add runtime approval for shell commands via interception by @krasserm in https://github.com/gradion-ai/ipybox/pull/51 Full Changelog: https://github.com/gradion-ai/ipybox/compare/0.8.2...0.9.0
0.8.20.8.2 · 15 Mar 2026What's Changed Add configurable kernel working directory behavior by @krasserm in https://github.com/gradion-ai/ipybox/pull/49 Full Changelog: https://github.com/gradion-ai/ipybox/compare/0.8.1...0.8.2
0.8.10.8.1 · 13 Mar 2026Fix KernelGateway stderr leak: redirect both stdout and stderr to DEVNULL when `log_to_stderr` is disabled Bump mcpygen to 0.1.3 Full Changelog: https://github.com/gradion-ai/ipybox/compare/0.8.0...0.8.1

README

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.

README fetched from the repository 4 days ago. The original is authoritative.

Questions

About ipybox

How do I install ipybox?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is ipybox safe to use with an AI agent?

Its trust score is 77 out of 100 (good). It passes 4 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is ipybox still maintained?

Yes — the latest release is 0.9.2 (1 Jun 2026), and the last commit was 4 months ago. The repository has 76 stars and 4 open issues.