Jupyter MCP Server
by Datalayer
Jupyter MCP Server is a Model Context Protocol (MCP) server implementation that provides interaction with Jupyter notebooks running in JupyterLab. It enables communication between applications like Claude Desktop and Jupyter notebooks.
Last updated: N/A
What is Jupyter MCP Server?
Jupyter MCP Server is an implementation of the Model Context Protocol (MCP) that allows external applications, such as Claude Desktop, to interact with Jupyter notebooks. It acts as a bridge, enabling these applications to execute code and manipulate notebook content.
How to use Jupyter MCP Server?
To use the server, first start JupyterLab with real-time collaboration enabled. Then, configure the client application (e.g., Claude Desktop) with the server's URL, token, and notebook path. The provided configuration examples for macOS, Windows, and Linux guide the user through this process, including setting up the necessary environment variables and Docker container.
Key features of Jupyter MCP Server
Model Context Protocol (MCP) support
Integration with JupyterLab
Real-time collaboration support
Dockerized deployment
Tools for adding and executing code cells
Tools for adding markdown cells
Use cases of Jupyter MCP Server
Integrating Jupyter notebooks with AI assistants like Claude
Automating notebook execution from external applications
Building interactive data analysis workflows
Extending the functionality of Jupyter notebooks with external tools
FAQ from Jupyter MCP Server
What is Model Context Protocol (MCP)?
What is Model Context Protocol (MCP)?
MCP is a protocol that enables communication and interaction between different applications and models.
How do I install JupyterLab?
How do I install JupyterLab?
You can install JupyterLab using pip: pip install jupyterlab jupyter-collaboration ipykernel
How do I configure Claude Desktop to use the Jupyter MCP Server?
How do I configure Claude Desktop to use the Jupyter MCP Server?
You need to add a configuration block to your claude_desktop_config.json file, specifying the server URL, token, and notebook path. Example configurations are provided in the README.
What tools are available in the server?
What tools are available in the server?
The server currently offers two tools: add_execute_code_cell for executing code and add_markdown_cell for adding markdown content.
How do I build the Docker image?
How do I build the Docker image?
You can build the Docker image using the command make build-docker.