development
location
documentation
public
jupyter
mcp
What is Jupyter Notebook?
connects Jupyter Notebook to Claude AI, allowing Claude to directly interact with and control Jupyter Notebooks. This integration enables AI-assisted code execution, data analysis, visualization, and more.
Documentation
JupyterMCP Documentation
Features
Two-way communication
Cell manipulation
Notebook management
Cell execution
Output retrieval
Installation# Prerequisites
Python 3.12 or newer
uv package manager
Claude AI desktop application
Setup
Clone or download this repository.
Create a virtual environment and install jupyter-mcp kernel.
(optional) Install additional Python packages.
Configure Claude desktop integration.
Usage# Starting the Connection
Start your Jupyter Notebook server.
Create a new Jupyter Notebook and choose the jupyter-mcp kernel.
Initialize the WebSocket server in a notebook cell.
Launch Claude desktop with MCP enabled.
Testing with External Client
You can test the functionality without using Claude Desktop with the included external client.
Troubleshooting
Connection Issues
Cell Execution Problems
WebSocket Port Conflicts
Limitations
Only supports Jupyter Notebook 6.x
Text output from cells is limited to 1500 characters