Jupyter Notebook MCP Server (for Cursor)

Name: Jupyter Notebook MCP Server (for Cursor)
Author: jbeno

@jbeno

Jupyter Notebook MCP Server (for Cursor) について

Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files

#jupyter #mcp #jupyter-notebook #ipynb #cursor #mcp-server #mcp-tools

基本情報

カテゴリ

メモリとナレッジ

ライセンス

NOASSERTION

ランタイム

python

トランスポート

stdio

公開者

jbeno

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "cursor-notebook-mcp": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "cursor-notebook-mcp"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Jupyter Notebook MCP Server (for Cursor)?

Jupyter Notebook MCP Server (for Cursor) is a Model Context Protocol server that allows AI agents within Cursor to interact directly with Jupyter Notebook (.ipynb) files. It overcomes Cursor’s limitation (as of version 0.50.5) where the agent mode could not edit notebooks or cells. The server uses nbformat for safe notebook manipulation and nbconvert for exporting, and restricts operations to user-defined directories for security.

How to use Jupyter Notebook MCP Server (for Cursor)?

Install with pip install cursor-notebook-mcp (Python 3.10+). Then start the server manually: cursor-notebook-mcp --transport streamable-http --allow-root /path/to/notebooks --host 127.0.0.1 --port 8080. Configure Cursor by adding a "notebook_mcp" entry to ~/.cursor/mcp.json with the server URL (http://127.0.0.1:8080/mcp).

Key features of Jupyter Notebook MCP Server (for Cursor)

Directly create, read, edit, delete, and move notebook cells
Supports code, markdown, and raw cell types
Export notebooks to Python, HTML, PDF, and more via nbconvert
Restricts file operations to user‑defined allowed roots
Provides tools for bulk cell adds, search, and outlining
Supports multiple transport modes: stdio, Streamable HTTP (recommended), and SSE

Use cases of Jupyter Notebook MCP Server (for Cursor)

AI agents editing notebook cells during interactive coding sessions in Cursor
Automating notebook creation, modification, and validation from agent prompts
Exporting notebooks to other formats (Python script, HTML, PDF) programmatically
Navigating and searching large notebooks to find and edit specific cells
Working with notebooks on remote SSH servers via SFTP support

FAQ from Jupyter Notebook MCP Server (for Cursor)

What limitation does this server address?

As of Cursor version 0.50.5, the agent mode could not edit Jupyter Notebook cells. This server provides MCP tools that enable direct cell manipulation.

Can this server be used with other tools besides Cursor?

Yes. Although designed for Cursor, it has no Cursor‑specific code beyond configuration instructions. It can be configured for VS Code (Insiders), Claude Code, or any MCP‑compatible agent.

What are the runtime requirements?

Python 3.10+ is required. All Python dependencies are installed automatically with the package. Optional external dependencies Pandoc and LaTeX are needed for certain nbconvert export formats (e.g., PDF).

How does the server ensure security?

The server restricts all file operations to directories specified via the --allow-root flag. This prevents the AI agent from accessing files outside the permitted paths.

What transport protocols are supported?

The server supports stdio, Streamable HTTP (recommended), and SSE (legacy) transports. Configuration for Cursor is provided for Streamable HTTP and SSE.

「メモリとナレッジ」の他のコンテンツ

Zettelkasten MCP Server

entanglr

A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.

159

Solomd

zhitongblog

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

425

Semantic Scholar MCP Server

YUZongmin

A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.

158