Skip to main content

Model Context Protocol (MCP) implementation for Jupyter notebooks to overcome limitation with Cursor

Project description

PyPI Version PyPI - Downloads Total Downloads License Python Version GitHub issues Last Commit Coverage Status

The Notebook MCP

A Model Context Protocol (MCP) server that enables AI agents to interact with Jupyter Notebook (.ipynb) files. Designed to overcome limitations with Cursor's AI agent mode, this tool allows AI assistants to directly manipulate notebook cells and structure through a secure, well-defined API.

Current Version: 0.9.0 - See the CHANGELOG.md for details on recent changes.

Why Use This?

  • For Cursor Users: Enables AI assistants to properly edit, create, and manipulate Jupyter notebooks.
  • For Data Scientists: No more copy-pasting AI output manually into your notebooks.
  • For Developers: Create complex notebook workflows with AI assistance while maintaining proper notebook structure.

Although originally designed for Cursor, this MCP server can be used with any MCP-compatible AI assistant tool, such as Claude Code.

Quick Start

# Install
uv pip install the-notebook-mcp

# Run (minimal example)
the-notebook-mcp --allow-root /path/to/your/notebooks

Video Walkthrough

Video Walkthrough Thumbnail

Cursor Jupyter Notebook MCP Server Tutorial demonstrates:

  • Installation and configuration
  • Creating notebooks from scratch
  • Using editing tools (edit, split, duplicate cells)
  • Working with notebook metadata
  • Exporting notebooks to Python

Features

The server provides the following MCP tools:

File Operations

  • notebook_create: Creates a new, empty notebook file
  • notebook_delete: Deletes an existing notebook file
  • notebook_rename: Renames/moves a notebook file from one path to another
  • notebook_export: Exports the notebook to another format (python, html, etc.)
  • notebook_validate: Validates the notebook structure against the nbformat schema

Reading Operations

  • notebook_read: Reads an entire notebook and returns its structure as a dictionary
  • notebook_read_cell: Reads the source content of a specific cell
  • notebook_get_cell_count: Returns the total number of cells
  • notebook_get_info: Retrieves general information about the notebook
  • notebook_get_outline: Generates a structural outline of the notebook (headings, definitions)
  • notebook_search: Searches for a string within all notebook cells

Cell Manipulation

  • notebook_add_cell: Adds a new code or markdown cell
  • notebook_edit_cell: Replaces the source content of a specific cell
  • notebook_delete_cell: Deletes a specific cell
  • notebook_move_cell: Moves a cell to a different position
  • notebook_change_cell_type: Changes a cell's type (code, markdown, or raw)
  • notebook_duplicate_cell: Duplicates a cell multiple times
  • notebook_split_cell: Splits a cell into two at a specified line number
  • notebook_merge_cells: Merges a cell with the one immediately following it
  • notebook_execute_cell: Executes a code cell and returns its outputs
    • Note: Requires an active Jupyter server
    • Example: notebook_execute_cell('/path/to/notebook.ipynb', 1, server_url='http://localhost:8888', token='your-token')
    • Kernel state is preserved between calls, allowing variables defined in earlier cells to be accessed in later cells

Metadata and Outputs

  • notebook_read_metadata: Reads the top-level notebook metadata
  • notebook_edit_metadata: Updates the top-level notebook metadata
  • notebook_read_cell_metadata: Reads the metadata of a specific cell
  • notebook_edit_cell_metadata: Updates the metadata of a specific cell
  • 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

Requirements

Python Dependencies

  • Python Version: ≥ 3.10

  • Core Dependencies: (automatically installed)

    • fastmcp ≥ 2.3.3
    • nbformat ≥ 5.0
    • nbconvert ≥ 6.0
    • ipython
    • jupyter_core
    • loguru ≥ 0.7.3
  • SSE Transport: (install with uv pip install "the-notebook-mcp[sse]")

    • uvicorn ≥ 0.20.0
    • starlette ≥ 0.25.0

External System Dependencies

For exporting to certain formats, you may need:

Installation

Standard Installation

# Basic installation (stdio transport only)
uv pip install the-notebook-mcp

# With SSE transport support
uv pip install "the-notebook-mcp[sse]"

Development Installation

  1. Clone the repository:

    git clone https://github.com/svallory/the-notebook-mcp.git
    cd the-notebook-mcp
    
  2. Create and activate a virtual environment:

    uv venv
    source .venv/bin/activate  # On Windows use `.venv\Scripts\activate`
    
  3. Install in development mode:

    uv pip install -e ".[dev]"
    
  4. Set up pre-commit hooks (recommended):

    pre-commit install
    

    See Pre-commit Hook Setup for details.

Running the Server

Basic Usage

# stdio transport (default)
the-notebook-mcp --allow-root /path/to/notebooks

# SSE transport
the-notebook-mcp --transport sse --allow-root /path/to/notebooks --host 0.0.0.0 --port 8889

Development Mode

Use one of these methods when working with the source code:

# Using poethepoet tasks
uv run poe start

# Using the Python module
python -m the_notebook_mcp.server --allow-root /path/to/notebooks

Available Tasks (poethepoet)

The project includes these predefined tasks:

  • start: Start the server with default settings
  • check-help: Show help information
  • check-version: Show version information
  • test: Run the test suite

Example:

# Show help
uv run poe check-help

# Run tests
uv run poe test

Command-Line Arguments

  • --allow-root: (Required) Path to a directory where notebooks are allowed (can be used multiple times)
  • --transport: stdio (default) or sse
  • --host: Host for SSE transport (default: 0.0.0.0)
  • --port: Port for SSE transport (default: 8889)
  • --max-cell-source-size: Maximum bytes for cell source (default: 10MB)
  • --max-cell-output-size: Maximum bytes for cell output (default: 10MB)
  • --log-dir: Directory for log files (default: ~/.the_notebook_mcp)
  • --log-level: DEBUG, INFO (default), WARNING, ERROR, CRITICAL

Cursor Integration

To configure Cursor to use this server, add settings to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-specific).

SSE Transport (Recommended)

Start the server separately, then configure Cursor:

{
  "mcpServers": {
    "notebook_mcp": {
      "url": "http://127.0.0.1:8889/sse"
    }
  }
}

stdio Transport

{
  "mcpServers": {
    "notebook_mcp": {
      "command": "/absolute/path/to/venv/bin/the-notebook-mcp",
      "args": [
        "--allow-root", "/absolute/path/to/your/notebooks"
      ]
    }
  }
}

Limitations and Security

  • Security Measures:
    • Paths are restricted to allowed root directories
    • Size limits on cell sources and outputs
    • Input validation for file extensions and types

Development & Testing

# Setup
uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"
pre-commit install

# Testing
uv run poe test

Known Issues

  • UI Refresh Issues: Some operations may succeed at the file level, but the Cursor UI might not update immediately. To fix, close and reopen the notebook or choose "Revert" when prompted.

Contributing

Contributions are welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes with tests
  4. Submit a pull request

See GitHub Issues for existing bugs or feature requests.

Acknowledgments

This project is based on the work of Jim Beno in cursor-notebook-mcp.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Author

Maintained by Saulo Vallory.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

the_notebook_mcp-0.9.0.tar.gz (175.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

the_notebook_mcp-0.9.0-py3-none-any.whl (37.1 kB view details)

Uploaded Python 3

File details

Details for the file the_notebook_mcp-0.9.0.tar.gz.

File metadata

  • Download URL: the_notebook_mcp-0.9.0.tar.gz
  • Upload date:
  • Size: 175.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.3

File hashes

Hashes for the_notebook_mcp-0.9.0.tar.gz
Algorithm Hash digest
SHA256 53da3f6ac8042381cd2d4197acd8a79f1c46b48dae53f4402171f0cc23545640
MD5 e06c10ce394e517a48bc15f797beacb4
BLAKE2b-256 9e1eaa3233a010ff64b840a296446369b641f545bfb540d3a513910067fb6990

See more details on using hashes here.

File details

Details for the file the_notebook_mcp-0.9.0-py3-none-any.whl.

File metadata

File hashes

Hashes for the_notebook_mcp-0.9.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d47dc2e012dbbaa120e3f15f5215a23e8ecc7045b474621bef226fa890fdec11
MD5 56af29856d88eb80ddbc40364425ef8c
BLAKE2b-256 b47b3ae4d8c4ad77b45772cde227dea955ad9fbfa9a726540adc2271a912e3cb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page