$ loading_
Control Colab notebooks, manage cells, and switch GPUs programmatically.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "colab-mcp (enhanced fork)" yet — see the docs or source repo.
Connect to the current Colab notebook, list all cells, reorganize imports, data processing, and training code into proper positions, remove duplicate cells, and run all code cells in order.
A reorganized cell structure, execution summary, and notes on deleted or moved cells.
Switch the current Colab runtime to an L4 GPU, or fall back to T4 if unavailable; then run the training cells and report the final GPU type and execution status.
GPU switching results, the actual hardware enabled, and a summary of whether training ran successfully.
Review the code cells in this Colab notebook and add short explanatory text cells before each major step, covering data loading, preprocessing, modeling, and evaluation.
Inserted explanatory text cells and an overview of the updated notebook structure.
Connect to Colab so AI can run and manage cloud notebooks.
Sync Colab notebook files via Google Drive without running notebook code.
Manage NotebookLM notebooks, sources, chats, and generated artifacts through MCP.
Load, edit, search, and save Jupyter notebooks through MCP tools.
Connect a local AI agent to Colab for code execution and file operations.
Control Google NotebookLM end-to-end for research, notes, chat, and exports.