広告掲載
MCP.so
ログイン

Jupyter MCP Server

@JosephLin11

リポジトリ

基本情報

カテゴリ

データと分析

ライセンス

BSD-3-Clause license

トランスポート

stdio

作者

JosephLin11

Jupyter MCP Server について

Jupyter MCP (Model Context Protocol) Server - Connect Jupyter notebooks with MCP-enabled applications

#jupyter-mcp-server#mcp#jupyter-notebooks

Jupyter MCP Server の設定

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": {
    "jupyter-mcp-server-josephlin11": {
      "command": "python",
      "args": [
        "tests/test_image_extraction.py"
      ]
    }
  }
}

Jupyter MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

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 MCP Server?

This server bridges AI agents (e.g., Claude) with Jupyter notebooks, enabling real‑time code execution, visualization generation, advanced image extraction (PNG/JPEG), and full notebook management through the Model Context Protocol (MCP). It is a fork of Datalayer’s original project, enhanced with improved documentation, error handling, and additional tools.

How to use 🚀 Jupyter MCP Server?

Prerequisites: Python 3.11+, Jupyter Notebook, and a compatible MCP client (e.g., Claude Desktop).
Install: Clone the repository, run pip install -r requirements.txt, then start Jupyter with the provided script (./scripts/start_jupyter.sh).
Configure Claude Desktop by adding the following to claude_desktop_config.json:

{
  "mcpServers": {
    "jupyter": {
      "command": "python",
      "args": ["/path/to/your/jupyter-mcp-server/src/jupyter_mcp_server.py"]
    }
  }
}

Run python3 scripts/get_claude_config.py to generate the correct configuration with current paths.

Key features of 🚀 Jupyter MCP Server

  • 18 comprehensive MCP tools for code execution, cell manipulation, and notebook operations.
  • Real‑time Jupyter integration via WebSocket for live code execution and kernel management.
  • Advanced image extraction – supports PNG and JPEG from matplotlib, seaborn, plotly.
  • Full notebook file operations – create, delete, switch, and list notebooks; CRUD on cells.
  • Automatic XSRF token management and token‑based authentication for Jupyter servers.
  • Robust error handling with fallback modes, logging, and resource cleanup.

Use cases of 🚀 Jupyter MCP Server

  • Data visualization pipeline: generate and extract multi‑panel plots (histograms, box plots) using matplotlib/seaborn.
  • Scientific computing: create 3D surface plots and complex visualizations, extract images for AI analysis.
  • Automated notebook workflows: programmatically add, modify, and reorder markdown/code cells.
  • Remote code execution and state persistence: maintain kernel state across AI agent sessions.
  • Integrating AI assistants with existing Jupyter environments for real‑time data exploration.

よくある質問

1

What image formats can be extracted?

PNG and JPEG images are supported. The server extracts base64‑encoded image data from matplotlib, seaborn, and plotly outputs.

2

What are the runtime requirements?

Python 3.11 or later, a running Jupyter Notebook server, and an MCP‑compatible client (e.g., Claude Desktop). Dependencies are listed in `requirements.txt`.

3

How does it handle authentication and security?

It automatically detects and manages XSRF tokens, supports token‑based Jupyter authentication, and implements graceful fallbacks for connection issues.

4

How does it compare to other Jupyter MCP servers?

This implementation offers 18 tools (vs. 10 or fewer in alternatives), supports both PNG and JPEG image extraction, provides automatic setup, works with all Jupyter versions, and uses WebSocket+HTTP for real‑time execution with automatic XSRF handling.

5

Where are notebooks stored?

All created notebooks are stored in the `notebooks/` directory inside the project folder. The default notebook is `mcp_notebook.ipynb`.

コメント

「データと分析」の他のコンテンツ

Statable

Key Arg B.V.

Privacy-first, cookieless web analytics hosted in the EU. Query visitors, pages, traffic sources, countries, goals, funnels and live traffic for your sites, and create sites, goals and funnels — 25 tools over OAuth.

Uxia

Uxia

Uxia brings AI user testing, usability testing and UX research into ChatGPT. It helps product managers, UX designers, researchers and developers evaluate websites, interactive prototypes and digital product experiences u

Aard

Braddon Lance

Aard connects Macroeconomic and other official data from 170+ publishers including World Bank, IMF, BIS, ECB, Eurostat, and National Statistical Offices. Aard is powered by a large graph of the metadata universe and an

IQFluence MCP

IQFluence

Influencer analytics for Instagram, TikTok and YouTube in your AI assistant: search 455M+ creators with audience filters, open influencer reports (audience demographics, fake followers, engagement), compare creators, che

Databar.ai

databar-ai

Databar.ai enables access to 100+ third party data providers, waterfall enrichments, and company signals via a single MCP server. It offers two additional products - Flows, which enable agents to build re-usable enrichme

広告掲載