Python Notebook

v1.0.0Data Science & MLstable

Lightweight Python Notebook MCP - Enable AI assistants to create, edit, and view Jupyter notebooks via Model Context Protocol

ai-toolsclaudeclaude-desktopcursor-idefastmcp
Share:
45
Stars
0
Downloads
0
Weekly
0/5

What is Python Notebook?

Python Notebook is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to lightweight python notebook mcp - enable ai assistants to create, edit, and view jupyter notebooks via model context protocol

Lightweight Python Notebook MCP - Enable AI assistants to create, edit, and view Jupyter notebooks via Model Context Protocol

This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Lightweight Python Notebook MCP - Enable AI assistants to cr

Use Cases

Create, edit, and view Jupyter notebooks via MCP
Enable AI assistants to work with Python notebooks
UsamaK98

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedApr 1, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx python-notebook

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Python Notebook

Python Notebook MCP Server enables AI assistants to create, read, edit, and manage Jupyter notebooks directly through the Model Context Protocol. It connects your MCP client (Claude Desktop, Cursor, etc.) to a local workspace of .ipynb files, allowing you to add cells, modify existing code, and inspect cell outputs without leaving your AI chat. Developers and data scientists use it to have their AI collaborator work hands-on inside notebooks rather than just generating code snippets to copy-paste.

Prerequisites

  • Python 3.10 or higher installed
  • uv package manager (https://astral.sh/uv)
  • fastmcp CLI installed via `uv pip install fastmcp` or `pipx install fastmcp`
  • An MCP-compatible client such as Claude Desktop or Cursor
  • Git to clone the repository
1

Clone the repository

Clone the python-notebook-mcp repository to your local machine.

git clone https://github.com/UsamaK98/python-notebook-mcp.git
cd python-notebook-mcp
2

Set up the Python environment

Create a virtual environment and install all required dependencies using uv. On macOS/Linux use the provided install script, or set up manually.

# Automated (macOS/Linux)
bash ./install_unix.sh

# Manual setup
uv venv
source .venv/bin/activate
uv pip install -r requirements.txt
3

Install the server in Claude Desktop

Use the fastmcp CLI to register the server with Claude Desktop under the name 'Jupyter Notebook MCP'.

fastmcp install server.py --name "Jupyter Notebook MCP"
4

Add server configuration manually (alternative)

If you prefer manual configuration, add the server to your MCP client config file using the path to your virtual environment's Python binary.

{
  "mcpServers": {
    "jupyter": {
      "command": "/path/to/python-notebook-mcp/.venv/bin/python",
      "args": ["/path/to/python-notebook-mcp/server.py"],
      "autoApprove": ["initialize_workspace"]
    }
  }
}
5

Initialize your workspace

The first tool call must always be initialize_workspace with the absolute path to the directory containing your notebooks. Relative paths are rejected.

6

Create and edit notebooks

Use natural language to create notebooks, add cells, read outputs, and edit existing cells. The server exposes tools: initialize_workspace, list_notebooks, create_notebook, read_notebook, read_cell, edit_cell, add_cell, read_cell_output, and read_notebook_outputs.

Python Notebook Examples

Client configuration

MCP client configuration for Claude Desktop pointing to the cloned server's Python binary.

{
  "mcpServers": {
    "jupyter": {
      "command": "/Users/you/python-notebook-mcp/.venv/bin/python",
      "args": ["/Users/you/python-notebook-mcp/server.py"],
      "autoApprove": ["initialize_workspace"]
    }
  }
}

Prompts to try

Example prompts to use after the server is connected and workspace is initialized.

- "Initialize the workspace at /Users/me/projects/data-analysis"
- "List all notebooks in the workspace"
- "Create a new notebook called 'sales_analysis.ipynb' with the title Sales Analysis"
- "Add a code cell to sales_analysis.ipynb that imports pandas and reads data.csv"
- "Read the output of cell 2 in sales_analysis.ipynb"
- "Edit cell 0 in sales_analysis.ipynb to fix the import statement"

Troubleshooting Python Notebook

initialize_workspace fails with 'relative path not allowed'

Always pass an absolute path (e.g. /Users/me/notebooks) to initialize_workspace. Relative paths like ./notebooks are rejected by the server.

Server not found after running fastmcp install

Restart Claude Desktop after installation. Also verify that the path to server.py in the config is absolute and that the .venv Python binary exists at the configured path.

uv command not found during setup

Install uv first: `curl -LsSf https://astral.sh/uv/install.sh | sh` on macOS/Linux, then open a new terminal so the PATH is updated before retrying.

Frequently Asked Questions about Python Notebook

What is Python Notebook?

Python Notebook is a Model Context Protocol (MCP) server that lightweight python notebook mcp - enable ai assistants to create, edit, and view jupyter notebooks via model context protocol It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Python Notebook?

Follow the installation instructions on the Python Notebook GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Python Notebook?

Python Notebook works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Python Notebook free to use?

Yes, Python Notebook is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "python-notebook": { "command": "npx", "args": ["-y", "python-notebook"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Python Notebook?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides