Jupyter Notebook
๐ ๐ - connects Jupyter Notebook to Claude AI, allowing Claude to directly interact with and control Jupyter Notebooks.
What is Jupyter Notebook?
Jupyter Notebook is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐ ๐ - connects jupyter notebook to claude ai, allowing claude to directly interact with and control jupyter notebooks.
๐ ๐ - connects Jupyter Notebook to Claude AI, allowing Claude to directly interact with and control Jupyter Notebooks.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- ๐ ๐ - connects Jupyter Notebook to Claude AI, allowing Claud
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx jupyter-notebookConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Jupyter Notebook
Jupyter Notebook MCP Server bridges Claude AI with a running Jupyter Notebook 6.x instance, enabling Claude to insert cells, execute code, read outputs, and manage notebook state through natural language. It works by running a WebSocket server inside the notebook that the MCP server communicates with, giving Claude real-time control over your data science environment. Data scientists and analysts can use it to automate EDA, generate and run code experiments, and iterate on notebooks conversationally.
Prerequisites
- Python 3.12+ recommended
- Jupyter Notebook 6.x specifically (incompatible with JupyterLab, Notebook v7, Google Colab, or VS Code)
- uv package manager installed (brew install uv on macOS)
- An MCP-compatible client such as Claude Desktop
- No external API keys required
Clone the repository
Clone the jupyter-notebook-mcp repository to get the MCP server source and WebSocket integration code.
git clone https://github.com/jjsantos01/jupyter-notebook-mcp.git
cd jupyter-notebook-mcpInstall dependencies with uv
Use uv to create a virtual environment and install the Jupyter kernel. Also install the ipykernel for the project-specific Python environment.
uv run python -m ipykernel install --name jupyter-mcpStart Jupyter Notebook 6.x
Launch Jupyter Notebook (classic version, not Lab) using uv. Note the URL and token printed in the console.
uv run jupyter nbclassicInitialize the WebSocket server in a notebook
Open a notebook in the browser and run this initialization code in the first cell. This starts the WebSocket server that bridges Claude to the notebook.
import sys
sys.path.append('/absolute/path/to/jupyter-notebook-mcp/src')
from jupyter_ws_server import setup_jupyter_mcp_integration
server, port = setup_jupyter_mcp_integration()Configure Claude Desktop
Add the MCP server configuration pointing to the src directory of the cloned repository. Replace /ABSOLUTE/PATH/TO/src with the real path on your system.
{
"mcpServers": {
"jupyter": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/jupyter-notebook-mcp/src",
"run",
"jupyter_mcp_server.py"
]
}
}
}Restart Claude Desktop and connect
Restart Claude Desktop to load the MCP server. Claude can now insert and execute cells, read outputs, and manage the notebook through conversation.
Jupyter Notebook Examples
Client configuration
Claude Desktop configuration running the Jupyter MCP server via uv from the cloned repository source directory. The WebSocket server must also be running inside the target notebook.
{
"mcpServers": {
"jupyter": {
"command": "uv",
"args": [
"--directory",
"/home/user/jupyter-notebook-mcp/src",
"run",
"jupyter_mcp_server.py"
]
}
}
}Prompts to try
Example prompts for controlling a Jupyter Notebook through Claude.
- "Look at the current notebook cells and add a new cell that loads the CSV from '/data/sales.csv' and prints its shape."
- "Run all cells in the notebook and show me any errors in the output."
- "Edit cell 3 to use seaborn instead of matplotlib for the bar chart, then re-run it and show me the image output."Troubleshooting Jupyter Notebook
WebSocket connection error: 'Connection refused on port 8765'
The WebSocket server must be initialized inside the running notebook first. Run the setup_jupyter_mcp_integration() cell in your notebook before connecting from Claude. If port 8765 is in use, the server auto-selects an alternative port โ check the cell output for the actual port.
Setup fails with 'jupyter nbclassic not found'
Install nbclassic explicitly: 'uv pip install jupyter nbclassic'. JupyterLab does not work โ this server requires the classic Jupyter Notebook 6.x interface specifically.
Claude cannot see notebook outputs after running cells
Use the get_cell_text_output or get_image_output tools explicitly in your prompt. Text output is capped at 1500 characters by default. For longer outputs, ask Claude to get a specific range of the output.
Frequently Asked Questions about Jupyter Notebook
What is Jupyter Notebook?
Jupyter Notebook is a Model Context Protocol (MCP) server that ๐ ๐ - connects jupyter notebook to claude ai, allowing claude to directly interact with and control jupyter notebooks. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Jupyter Notebook?
Follow the installation instructions on the Jupyter Notebook GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Jupyter Notebook?
Jupyter Notebook works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Jupyter Notebook free to use?
Yes, Jupyter Notebook is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Jupyter Notebook Alternatives โ Similar Data Science & ML Servers
Looking for alternatives to Jupyter Notebook? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
โ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
โ 3.1k๐ ๐ - MCP server that exposes RocketRide AI pipelines as t
Aix Db
โ 2.1kAix-DB ๅบไบ LangChain/LangGraph ๆกๆถ๏ผ็ปๅ MCP Skills ๅคๆบ่ฝไฝๅไฝๆถๆ๏ผๅฎ็ฐ่ช็ถ่ฏญ่จๅฐๆฐๆฎๆดๅฏ็็ซฏๅฐ็ซฏ่ฝฌๆขใ
NeMo Data Designer
โ 1.9k๐จ NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
โ 1.7kOpen source implementation and extension of Google Researchโs PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
โ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Jupyter Notebook in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Jupyter Notebook?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.