MCP·10C475
J

jupyter-notebook-mcp

By jjsantos01·Visit Source
Jupyter Notebook integration with Claude AI via MCP
April 17, 2025
2 months ago
1 Clicks
About jupyter-notebook-mcp

Jupyter Notebook integration with Claude AI via MCP. jupyter-notebook-mcp is a Model Context Protocol (MCP) server maintained by jjsantos01. It connects to MCP-compatible clients such as Claude Desktop, Cursor, Cline, and other agents that speak the protocol. It exposes 11 tools, including ping, insert_and_execute_cell, save_notebook, get_cells_info, get_notebook_info, run_cell, run_all_cells and get_cell_text_output, that an agent can call directly. It is categorized under AI/Claude and Tool/Jupyter.

What is this MCP

This MCP enables bidirectional communication between Jupyter Notebook (v6.x) and Claude AI, allowing the AI to directly manipulate notebook cells, execute code, and retrieve outputs through a WebSocket-based server.

How to use this MCP

  • Install prerequisites (Python 3.12+, uv package manager)
  • Configure Claude desktop with MCP server path
  • Start Jupyter Notebook with the custom kernel
  • Initialize WebSocket server in a notebook cell
  • Interact through Claude's MCP-enabled interface
  • What this MCP can be used for

    - AI-assisted code execution and debugging

    - Automated data analysis and visualization

    - Interactive educational demonstrations

    - Research workflow automation

    - Presentation generation with live code examples

    Repository Info
    Stars:
    128
    Forks:
    25
    Watchers:
    128
    Last Updated: 2 months ago

    AIMCP authority

    DR and traffic signal for the AIMCP public domain.

    FAQ

    Frequently asked questions

    What is the jupyter-notebook-mcp MCP server?

    jupyter-notebook-mcp is a Model Context Protocol server from jjsantos01. It lets MCP-compatible AI clients call its tools over a standard interface, so agents like Claude, Cursor, and Cline can use it without custom integration.

    How do I connect jupyter-notebook-mcp to my AI client?

    Add jupyter-notebook-mcp to your client's MCP configuration using the stdio or SSE connection shown in the usage examples on this page, then restart the client to load the server.

    What tools does jupyter-notebook-mcp provide?

    jupyter-notebook-mcp provides 11 tools: ping, insert_and_execute_cell, save_notebook, get_cells_info, get_notebook_info, run_cell, run_all_cells, get_cell_text_output, get_image_output, edit_cell_content and set_slideshow_type.

    Is jupyter-notebook-mcp free to use?

    jupyter-notebook-mcp is listed on AIMCP for free. Any API keys or accounts required by the underlying service are set by its provider.

    Sponsored

    Vernclaw Plugins for OpenClaw

    Ready-to-use connectors for SEO data, social reading & content generation. Pay-as-you-go credits with audit logs.