loading…
Search for a command to run...
loading…
Provides AI assistants with deep semantic and runtime understanding of Jupyter notebooks.
Provides AI assistants with deep semantic and runtime understanding of Jupyter notebooks.
AI-Native Intelligence for Jupyter Notebooks
Notebook MCP is a Model Context Protocol (MCP) server that gives AI assistants deep semantic and runtime understanding of .ipynb notebooks.
AI coding assistants struggle with notebooks because notebooks rely heavily on execution order and hidden runtime state.
Notebook MCP bridges this gap by converting notebooks into structured, analyzable execution graphs.
Notebook → MCP Server → AI Assistant
Core Components:
npm install -g @akram1110/notebook-mcp
pip install notebook-mcp
notebook-mcp
Notebook MCP installs components via both npm and pip.
Follow the steps below to fully remove the tool.
npm uninstall -g @akram1110/notebook-mcp
pip uninstall notebook-mcp
or
python -m pip uninstall notebook-mcp
notebook-mcp
Expected output:
command not found
Python sometimes leaves launcher files behind.
Check:
where notebook-mcp
If found, delete from:
<python_install_dir>\Scripts\
Example:
C:\Users\<username>\AppData\Local\Programs\Python\Python311\Scripts\
If pip shows:
WARNING: Ignoring invalid distribution ~
Delete folders beginning with ~ inside:
<python_install_dir>\Lib\site-packages\
Then verify:
pip check
pip cache purge
After completing these steps, Notebook MCP will be fully removed from your system.
{
"mcpServers": {
"notebook": {
"command": "notebook-mcp"
}
}
}
| Tool | Description |
|---|---|
| notebook_analyze | Builds dependency graph |
| notebook_context | Generates focused context |
| notebook_state | Detects execution state |
| notebook_rerun_plan | Suggests rerun order |
| jupyter_execute | Executes kernel code |
| jupyter_inspect | Inspects runtime variables |
Set environment variables:
JUPYTER_BASE_URL=http://localhost:8888
JUPYTER_TOKEN=<token>
Issues and PRs welcome.
MIT License
Run in your terminal:
claude mcp add notebook-mcp -- npx Security
Low riskAutomated heuristic from public metadata — not a security guarantee.