# jupyter-mcp-server

> MCP Server

Jupyter MCP Server is a Model Context Protocol server that enables interaction with Jupyter notebooks running in a local JupyterLab environment. It facilitates real-time collaboration and integration with tools like Claude Desktop.

## Overview

- **Category:** AI
- **Language:** Python
- **Stars:** 1276
- **Forks:** 4
- **Owner:** datalayer
- **GitHub:** https://github.com/datalayer/jupyter-mcp-server
- **Homepage:** https://datalayer.io
- **Created:** 2025-02-12T06:41:35+00:00
- **Updated:** 2025-03-28T11:13:03+00:00
- **Source:** https://model-context-protocol.com/servers/jupyter-model-context-protocol-mcp-server

## Setup

## Setup

1.  Install `jupyterlab`, `jupyter-collaboration`, and `ipykernel` using `pip install jupyterlab jupyter-collaboration ipykernel`.
2.  Start JupyterLab with the command: `jupyter lab --port 8888 --IdentityProvider.token MY_TOKEN --ip 0.0.0.0`.
3.  Add the MCP server configuration to your `claude_desktop_config.json` depending on your OS (MacOS, Windows, or Linux), ensuring the `SERVER_URL` and `TOKEN` match those used in the `jupyter lab` command and the `NOTEBOOK_PATH` is relative to the directory where JupyterLab was started.
4.  For MacOS and Windows, the configuration includes running a Docker container with environment variables for `SERVER_URL`, `TOKEN`, and `NOTEBOOK_PATH`.
5.  For Linux, the configuration is similar but includes the `--network=host` option and uses `http://localhost:8888` for the `SERVER_URL`.

## Tools

## Available Tools

1.  `add_execute_code_cell` (Add and execute a code cell in a Jupyter notebook.)
2.  `add_markdown_cell` (Add a markdown cell in a Jupyter notebook.)
3.  `download_earth_data_granules` (Add a code cell in a Jupyter notebook to download Earth data granules from NASA Earth Data.)