Jupyter MCP Server for Claude Desktop

@harshitha-8

代码仓库

基本信息

分类

数据与分析

传输方式

stdio

作者

harshitha-8

关于 Jupyter MCP Server for Claude Desktop

Jupyter MCP Server Jupyter MCP Server is an implementation of the Model Context Protocol (MCP) server that enables interaction with Jupyter notebooks running in any JupyterLab environment, including your local JupyterLab instance

#jupyter #mcp #claude-desktop

Jupyter MCP Server for Claude Desktop 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "Integrating-the-Jupyter-server-with-claude-desktop-uisng-the-powerful-model-context-protocol": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@datalayer/jupyter-mcp-server",
        "--client",
        "claude"
      ]
    }
  }
}

Jupyter MCP Server for Claude Desktop 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Jupyter MCP Server for Claude Desktop?

Jupyter MCP Server for Claude Desktop is an implementation of the Model Context Protocol (MCP) server that enables interaction with Jupyter notebooks running in any JupyterLab environment, including local instances. It is designed for seamless integration with Claude Desktop across macOS, Windows, and Linux.

How to use Jupyter MCP Server for Claude Desktop?

Install the server Docker image or use Smithery, configure it in Claude Desktop’s MCP settings with environment variables SERVER_URL, TOKEN, and NOTEBOOK_PATH, then start JupyterLab on port 8888. The server provides two tools: add_execute_code_cell and add_markdown_cell.

Key features of Jupyter MCP Server for Claude Desktop

Provides an MCP server interface for Jupyter notebooks.
Supports real-time collaboration via JupyterLab.
Integrates smoothly with Claude Desktop on all platforms.
Programmatically add and execute code or markdown cells.
Runs inside Docker for easy deployment.

Use cases of Jupyter MCP Server for Claude Desktop

Let Claude interactively execute Python code in a Jupyter notebook.
Automate notebook cell creation and execution from AI conversations.
Enable collaborative data analysis with AI assistance.
Integrate JupyterLab workflows with Claude Desktop’s MCP capabilities.

常见问题

What dependencies are required to run the server?

You need JupyterLab 4.4.1, jupyter-collaboration 4.0.2, ipykernel, and datalayer_pycrdt 0.12.15. The server itself runs in Docker.

How do I configure the server for Linux vs macOS/Windows?

On Linux use `--network=host` and `http://localhost:8888`; on macOS/Windows use `http://host.docker.internal:8888`. The `TOKEN` must match your JupyterLab setup.

Can I install the server without Docker?

The README only describes Docker usage and Smithery installation via `npx`. No native install is documented.

What tools does the server expose?

Two tools: `add_execute_code_cell` (takes `cell_content` string, returns cell output) and `add_markdown_cell` (takes `cell_content` string, returns success message).

Where does the notebook file live?

The `NOTEBOOK_PATH` environment variable defines the notebook file name (e.g., `notebook.ipynb`), relative to the directory where JupyterLab is started.

数据与分析分类下的更多 MCP 服务器

Altss Public Profiles MCP

Altss

Anonymous, read-only search and reads of published Altss company-profile summaries, with canonical citations. Hosted HTTP and npm stdio connections; no private app data or account access.

Forency

cheevahagadog

Investigate any website's technology stack: CMS, eCommerce, frameworks, analytics, CRM, payments, and hosting behind any URL. Ask "which of these 15 prospects use HubSpot vs Salesforce?" and get a table back. Free tier:

Instagram MCP Server

HasData

Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.

ScrapeCheck

FieldmodeLLC

Verify scraped data against the live source page. Signed verdicts, $0.01 via x402.

Zillow MCP Server