cursor-notebook-mcp

Overview

cursor-notebook-mcp is a Python-based Model Context Protocol server designed to help AI agents interact with Jupyter Notebook files. It provides comprehensive tools for creating, reading, editing, and exporting notebook files, addressing a specific limitation where Cursor couldn't directly edit notebooks in Agent mode. The server uses nbformat for safe manipulation and nbconvert for export functionality, with security measures to restrict operations to user-defined directories.

Try asking AI

After installing, here are 6 things you can ask your AI assistant:

• notebook_create

  Creates a new, empty notebook file.

  Try:Create a new empty notebookTry:Start a new data analysis notebook
• notebook_read

  Reads an entire notebook and returns its structure as a dictionary.

  Try:Read the contents of my notebook.ipynbTry:Show me all cells in the analysis notebook
• notebook_add_cell

  Adds a new code or markdown cell after a specified index.

  Try:Add a new code cell after cell 3Try:Insert a markdown cell explaining the results
• notebook_edit_cell

  Replaces the source content of a specific cell.

  Try:Update cell 5 with new visualization codeTry:Fix the error in cell 2
• notebook_delete_cell

  Deletes a specific cell.

  Try:Remove cell 4 which has no outputTry:Delete the markdown introduction cell
• notebook_export

  Exports the notebook to another format (e.g., python, html).

  Try:Export the notebook to Python scriptTry:Convert my analysis to HTML format
• notebook_split_cell

  Splits a cell into two at a specified line number.

  Try:Split cell 3 after line 5Try:Divide the long cell into two parts
• notebook_merge_cells

  Merges a cell with the cell immediately following it.

  Try:Combine cell 4 and cell 5Try:Merge adjacent analysis cells
• notebook_search

  Searches cells for a keyword, showing contextual snippets.

  Try:Search for 'matplotlib' in the notebookTry:Find cells containing 'pandas'
• notebook_get_outline

  Produces an outline showing cell numbers with major headings/functions.

  Try:Show me the notebook structureTry:Generate an outline of the analysis notebook
• notebook_clear_all_outputs

  Clears outputs and execution counts for all code cells.

  Try:Reset all cell outputsTry:Clear the notebook before running fresh
• notebook_rename

  Renames/moves a notebook file from one path to another.

  Try:Rename my_notebook.ipynb to final_analysis.ipynbTry:Move the notebook to the reports folder

Comparable tools

Installation

pip install cursor-notebook-mcp

git clone https://github.com/jbeno/cursor-notebook-mcp.git
cd cursor-notebook-mcp
python -m venv .venv
source .venv/bin/activate  # On Windows use `.venv\Scripts\activate`
pip install -e .

{
  "mcpServers": {
    "notebook_mcp": {
      "url": "http://127.0.0.1:8080/mcp"
    }
  }
}

cursor-notebook-mcp --transport streamable-http --allow-root /path/to/your/notebooks --host 127.0.0.1 --port 8080

FAQ

What transport modes does this server support?

The server supports stdio, Streamable HTTP, and SSE transport modes. Streamable HTTP is recommended for new setups.

Can this server be used with other AI tools besides Cursor?

Yes, although designed for Cursor, this server can be configured for use with VS Code (Insiders), Claude Code, or any model/agent that supports MCP.

What external dependencies are required for export functionality?

Pandoc is required for most non-HTML export formats. For PDF export, LaTeX (XeLaTeX recommended) is also required by nbconvert.

Compare cursor-notebook-mcp with