Model Context Protocol (MCP) Server: io.github.gradion-ai/ipybox

The ipybox MCP server provides a unified execution environment for running Python code, shell commands, and making programmatic MCP tool calls. It is described as a sandbox/runtime used for code execution and tool calling within an MCP-based workflow.

🛠️ Key Features

Unified execution environment for Python, shell commands, and MCP tool calls
Includes MCP-related concepts such as mcp, mcp-client, and mcp-server
Supports ipython and a sandbox-runtime approach

🚀 Use Cases

Execute Python code in a controlled environment
Run shell commands alongside Python execution
Call MCP tools programmatically as part of a “code mode” workflow

⚡ Developer Benefits

Consolidates multiple execution types (Python, shell, MCP tool calls) into one environment
Aligned with MCP tooling categories and “programmatic-tool-calling”

⚠️ Limitations

The provided data does not specify tool availability, configuration options, or compatibility details.

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.

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.

Install

Configuration

Arguments

--workspace

directory_path

--sandbox

--sandbox-config

file_path

--log-level

DEBUG|INFO|WARNING|ERROR|CRITICAL

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "ipybox": {
      "command": "uvx",
      "args": [
        "ipybox",
        "--workspace",
        "--sandbox",
        "--sandbox-config",
        "--log-level"
      ]
    }
  }
}

io.github.gradion-ai/ipybox