mcpField
I
ipybox

ipybox

Local
github.com/gradion-aiDeveloper Tools76Updated 20w ago
Repository

About ipybox

ipybox is a unified execution environment that runs Python code, shell commands and programmatic MCP tool calls in a stateful IPython kernel. It runs locally and is aimed at developers who need protected access to local data and tools.

Key features

  1. 01Stateful execution in IPython kernels
  2. 02Combines Python, shell and MCP calls in one block
  3. 03Generates typed Python APIs from MCP tool schemas
  4. 04Approval for individual tool calls and shell commands
  5. 05Optional OS-level kernel sandboxing

Use cases

  1. 01Letting agents call MCP tools through code instead of JSON
  2. 02Running agent-generated code locally under controlled conditions
  3. 03Adding a code action skill to Claude Code

MCP support

ipybox can run as an MCP server that offers code execution and programmatic tool calling to MCP clients. It also generates Python APIs for tools from MCP servers.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "gradion-ai-ipybox": {
      "command": "uvx",
      "args": [
        "ipybox"
      ]
    }
  }
}
Run commanduvx ipybox

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiipybox0.9.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

ipybox

ipybox

mcp-name: io.github.gradion-ai/ipybox

Website PyPI - Version GitHub Release GitHub Actions Workflow Status GitHub License

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

CapabilityDescription
Stateful executionState persists across executions in IPython kernels
Unified executionCombine Python code, shell commands, and programmatic MCP tool calls in a code block
Shell command executionRun shell commands via !cmd syntax, capture output into Python variables
Programmatic MCP tool callsMCP tools called via generated Python API ("code mode"), not JSON directly
Python tool API generationTyped functions and Pydantic models generated from MCP tool schemas via mcpygen
Application-level approvalIndividual approval of tool calls and shell commands during code execution
Lightweight sandboxingOptional kernel isolation via Anthropic's sandbox-runtime
Local executionNo cloud dependencies, everything runs locally on your machine

Usage

ComponentDescription
Python SDKPython API for building applications on ipybox
MCP serveripybox as MCP server for code actions and programmatic tool calling
Claude Code pluginPlugin that bundles the ipybox MCP server and a code action skill

Tip

Freeact agent

Freeact is a general-purpose agent built on ipybox.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.