Cursor Notebook MCP
This project is a Jupyter Notebook MCP server designed for the Cursor editor, providing a set of tools that allow AI agents to directly operate on cells in .ipynb files, solving the limitation that Cursor cannot directly edit notebook content in agent mode.
rating : 2 points
downloads : 7
What is the Jupyter Notebook MCP Server?
This is an MCP server specifically designed for Cursor, allowing AI to directly edit and operate Jupyter notebooks (.ipynb) files. It solves the problem that notebooks cannot be directly edited in Cursor.How to use the Jupyter Notebook MCP Server?
By configuring Cursor's MCP server, you can easily enable AI's full editing capabilities for Jupyter notebooks. You can start using it in just a few steps.Applicable Scenarios
Suitable for users who need to frequently use Jupyter notebooks for data analysis, machine learning model development, and teaching demonstrations.Main Features
Create NotebookCreate a new empty notebook file in the specified directory.
Delete NotebookDelete an existing notebook file.
Rename NotebookMove the notebook file from one path to another.
Read NotebookRead the entire notebook and return its structure as a dictionary.
Edit CellReplace the content of a specific cell.
Export NotebookExport the notebook to other formats (such as Python script, HTML, etc.).
Advantages and Limitations
Advantages
Supports AI to directly edit Jupyter notebooks.
Ensures the integrity of the notebook structure.
Provides a rich set of APIs to operate on notebook content.
Limitations
Does not support cell execution function.
Requires manual configuration of Cursor to use the server.
Some advanced export functions may require additional dependencies (such as LaTeX).
How to Use
Install the Server
Install the server via pip and activate the virtual environment.
Start the Server
Run the server script and specify the allowed root directory.
Configure Cursor
Add the server URL to Cursor's MCP configuration.
Usage Examples
Create a New NotebookCreate a new Jupyter notebook file through Cursor.
Edit Cell ContentUse AI tools to edit specific cells in the notebook.
Export NotebookExport the notebook as a Python script.
Frequently Asked Questions
How to install the Jupyter Notebook MCP server?
Why can't cells be executed directly?
How to solve the UI refresh problem?
Related Resources
Project Homepage
Project source code and documentation.
Installation Guide
Detailed installation and configuration instructions.
Video Tutorial
A video tutorial for quickly understanding the server's functions.
Featured MCP Services

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
823
4.3 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
79
4.3 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
130
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
554
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.6K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
745
4.8 points