Advertise
MCP.so
Sign In

Jupyter Notebook MCP Server (for Cursor)

@jbeno

RepositoryHomepage

Basic information

Category

Memory & Knowledge

License

NOASSERTION

Transports

stdio

Author

jbeno

About Jupyter Notebook MCP Server

Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files

#jupyter#mcp#jupyter-notebook#ipynb#cursor#mcp-server#mcp-tools

Jupyter Notebook MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "cursor-notebook-mcp": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "cursor-notebook-mcp"
      ]
    }
  }
}

Jupyter Notebook MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Jupyter Notebook MCP Server (for Cursor)?

Jupyter Notebook MCP Server (for Cursor) is a Model Context Protocol server that allows AI agents within Cursor to interact directly with Jupyter Notebook (.ipynb) files. It overcomes Cursor’s limitation (as of version 0.50.5) where the agent mode could not edit notebooks or cells. The server uses nbformat for safe notebook manipulation and nbconvert for exporting, and restricts operations to user-defined directories for security.

How to use Jupyter Notebook MCP Server (for Cursor)?

Install with pip install cursor-notebook-mcp (Python 3.10+). Then start the server manually: cursor-notebook-mcp --transport streamable-http --allow-root /path/to/notebooks --host 127.0.0.1 --port 8080. Configure Cursor by adding a "notebook_mcp" entry to ~/.cursor/mcp.json with the server URL (http://127.0.0.1:8080/mcp).

Key features of Jupyter Notebook MCP Server (for Cursor)

  • Directly create, read, edit, delete, and move notebook cells
  • Supports code, markdown, and raw cell types
  • Export notebooks to Python, HTML, PDF, and more via nbconvert
  • Restricts file operations to user‑defined allowed roots
  • Provides tools for bulk cell adds, search, and outlining
  • Supports multiple transport modes: stdio, Streamable HTTP (recommended), and SSE

Use cases of Jupyter Notebook MCP Server (for Cursor)

  • AI agents editing notebook cells during interactive coding sessions in Cursor
  • Automating notebook creation, modification, and validation from agent prompts
  • Exporting notebooks to other formats (Python script, HTML, PDF) programmatically
  • Navigating and searching large notebooks to find and edit specific cells
  • Working with notebooks on remote SSH servers via SFTP support

Frequently asked questions

1

What limitation does this server address?

As of Cursor version 0.50.5, the agent mode could not edit Jupyter Notebook cells. This server provides MCP tools that enable direct cell manipulation.

2

Can this server be used with other tools besides Cursor?

Yes. Although designed for Cursor, it has no Cursor‑specific code beyond configuration instructions. It can be configured for VS Code (Insiders), Claude Code, or any MCP‑compatible agent.

3

What are the runtime requirements?

Python 3.10+ is required. All Python dependencies are installed automatically with the package. Optional external dependencies Pandoc and LaTeX are needed for certain nbconvert export formats (e.g., PDF).

4

How does the server ensure security?

The server restricts all file operations to directories specified via the `--allow-root` flag. This prevents the AI agent from accessing files outside the permitted paths.

5

What transport protocols are supported?

The server supports stdio, Streamable HTTP (recommended), and SSE (legacy) transports. Configuration for Cursor is provided for Streamable HTTP and SSE.

Comments

More Memory & Knowledge MCP servers

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

1

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

Snipara

alopez3006

MCP connector for Snipara, the Project Brain for AI coding agents

1

Orcha

westonhancock

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

Leviathan Systems Public Content MCP

Leviathan Systems

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

Advertise