notebook
<!-- ~ Copyright (c) 2024- Datalayer, Inc. ~ ~ BSD 3-Clause License -->
<!-- ~ Copyright (c) 2024- Datalayer, Inc. ~ ~ BSD 3-Clause License -->
How it fires
How this command gets triggered: by you, by Claude, or both.
/runContext preview
What this command does when you run it.
<!-- ~ Copyright (c) 2024- Datalayer, Inc. ~ ~ BSD 3-Clause License -->
<!-- ~ Copyright (c) 2024- Datalayer, Inc. ~ ~ BSD 3-Clause License -->
--- description: Run a cell, or the whole notebook, on Datalayer argument-hint: [cell index, "all", or a description] ---
Execute code in the Datalayer notebook we are working in.
Execution happens on the server, so it keeps running whether or not this session stays open. Say so when a computation looks long.
Steps:
1. If no notebook is active, run `/datalayer:notebook` first. 2. Work out what `$ARGUMENTS` means:
confirm before running it. 3. Report what each cell produced. If a cell fails, show the error and offer a fix rather than retrying blindly.
Never edit a cell to make it pass without saying what you changed and why.
An MCP server developed for AI to connect and manage Jupyter Notebooks in real-time — and scale your Code Sandbox from local to the cloud (Datalayer, Kaggle, Google Colab, Modal, Daytona, E2B, CoreWeave, Cloudflare...)
Repo: datalayer/jupyter-mcp-server
<!-- ~ Copyright (c) 2024- Datalayer, Inc. ~ ~ BSD 3-Clause License -->