Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Easy Jupyter Editor

БесплатноНе проверен

Enables AI agents to safely and structurally edit Jupyter Notebook (.ipynb) files by providing tools to read, edit, add, and delete cells without corrupting the

GitHubEmbed

Описание

Enables AI agents to safely and structurally edit Jupyter Notebook (.ipynb) files by providing tools to read, edit, add, and delete cells without corrupting the JSON structure.

README

A lightweight Model Context Protocol (MCP) server designed to allow AI Agents to safely and structurally edit Jupyter Notebook (.ipynb) files.

Background

This MCP server was developed to enable AI agents to safely manipulate Jupyter Notebook (.ipynb) files.

In many AI agent environments (such as Antigravity), directly executing notebook files or editing complex .ipynb JSON structures as raw text can be difficult due to security restrictions or the risk of corrupting the file format.

This project aims to "structurally edit Notebook files correctly while bypassing execution permission issues." By using the nbformat library, it allows adding, editing, and deleting cells without breaking the JSON structure.

Features

Provides the following tools:

  • read_notebook: Retrieves a list of cells (index and content summary) from a Notebook.
  • get_cell: Retrieves the full source code of a specific cell by index.
  • edit_cell: Modifies the content of a specific cell.
  • add_cell: Adds a new code or Markdown cell.
  • delete_cell: Deletes a specific cell.
  • create_notebook: Creates a new, empty Notebook.

Installation & Usage

It is recommended to run this server using uv.

1. Claude Desktop / MCP Client Configuration

Add the following configuration to claude_desktop_config.json.

Using PyPI (Recommended)

This is the simplest way to run the server.

{
  "mcpServers": {
    "easy-jupyter-editor": {
      "command": "uvx",
      "args": ["easy-jupyter-editor-mcp"]
    }
  }
}

Running directly from GitHub

{
  "mcpServers": {
    "easy-jupyter-editor": {
      "command": "uv",
      "args": [
        "run",
        "--from",
        "git+https://github.com/YourUsername/easy-jupyter-editor-mcp",
        "easy-jupyter-editor-mcp"
      ]
    }
  }
}

Running Locally for Development

{
  "mcpServers": {
    "easy-jupyter-editor": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "--with",
        "nbformat",
        "python",
        "/absolute/path/to/easy-jupyter-editor-mcp/src/easy_jupyter_editor_mcp/__init__.py"
      ]
    }
  }
}

Development

# Build
uv build

# Publish to PyPI
uv publish

from github.com/cshara1/easy-jupyter-editor-mcp

Установка Easy Jupyter Editor

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/cshara1/easy-jupyter-editor-mcp

FAQ

Easy Jupyter Editor MCP бесплатный?

Да, Easy Jupyter Editor MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Easy Jupyter Editor?

Нет, Easy Jupyter Editor работает без API-ключей и переменных окружения.

Easy Jupyter Editor — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить Easy Jupyter Editor в Claude Desktop, Claude Code или Cursor?

Открой Easy Jupyter Editor на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare Easy Jupyter Editor with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории ai