cursor-rules

Jupyter Notebook Rules for Cursor (Using the-notebook-mcp MCP server):

1. Tool Usage:

   • Always use the tools provided by the the-notebook-mcp server for operations on Jupyter Notebook (.ipynb) files.
   • Avoid using the standard edit_file tool on .ipynb files, as this can corrupt the notebook structure.

2. Investigation Strategy:

   • A comprehensive suite of tools is available to inspect notebooks. If the user mentions an issue, a specific cell, or asks for a modification, first attempt to gather context independently.
   • Use the available tools to examine the notebook structure, content, metadata, and outputs to locate the relevant context or identify the problem.
   • Ask the user for clarification only if the necessary information cannot be determined after using the investigation tools.

3. Available Tools:

   • Notebook File Tools:

     • notebook_create: Creates a new, empty notebook file.
     • notebook_delete: Deletes an existing notebook file.
     • notebook_read: Reads an entire notebook and returns its structure as a dictionary.
     • notebook_rename: Renames/moves a notebook file from one path to another.

   • Cell Manipulation tools:

     • notebook_add_cell: Adds a new code or markdown cell after a specified index.
     • notebook_change_cell_type: Changes a cell's type (code, markdown, or raw).
     • notebook_delete_cell: Deletes a specific cell.
     • notebook_duplicate_cell: Duplicates a cell multiple times (default: once).
     • notebook_edit_cell: Replaces the source content of a specific cell.
     • notebook_get_cell_count: Returns the total number of cells.
     • notebook_get_info: Retrieves general information (cell count, metadata, kernel, language info).
     • notebook_merge_cells: Merges a cell with the cell immediately following it.
     • notebook_move_cell: Moves a cell to a different position.
     • notebook_read_cell: Reads the source content of a specific cell.
     • notebook_split_cell: Splits a cell into two at a specified line number.

   • Cell Output Tools:

     • notebook_read_cell_output: Reads the output list of a specific code cell.
     • notebook_clear_cell_outputs: Clears the outputs and execution count of a specific cell.
     • notebook_clear_all_outputs: Clears outputs and execution counts for all code cells.

   • Notebook Metadata Tools:

     • notebook_read_metadata: Reads the top-level notebook metadata.
     • notebook_edit_metadata: Updates the top-level notebook metadata.

   • Cell Metadata Tools:

     • notebook_read_cell_metadata: Reads the metadata of a specific cell.
     • notebook_edit_cell_metadata: Updates the metadata of a specific cell.

   • Utility Tools:

     • notebook_validate: Validates the notebook structure against the nbformat schema.
     • notebook_export: Exports the notebook to another format (e.g., python, html) using nbconvert. Note: See External Dependencies below for requirements needed for certain export formats like PDF.

4. Math Notation: For LaTeX in Markdown cells, use $ ... $ for inline math and $$ ... $$ for display math. Avoid \( ... \) and \[ ... \].

5. Cell Magics:

   • Avoid unsupported cell magics like %%bash, %%timeit, and %%writefile.
   • Use !command for shell commands instead of %%bash.
   • Use %timeit (line magic) for timing single statements.
   • %%html works for rendering HTML output.
   • %%javascript can execute (e.g., alert), but avoid relying on it for manipulating cell output display.

6. Rich Outputs: Matplotlib, Pandas DataFrames, Plotly, ipywidgets (tqdm.notebook), and embedded HTML in Markdown generally render correctly.

7. Mermaid: Diagrams in ```mermaid ``` blocks are not rendered by default.

8. Character Escaping in source Parameter: