Colab-MCP (unofficial)

Download one file from the VM into the working directory.

Download a whole VM folder into `local_dir` (inside the working directory) via one zip. Refuses archives whose paths escape the target or exceed COLAB_MCP_MAX_DOWNLOAD_MB (default 1024).

Step 2 of mounting Google Drive: call it AFTER the user says they clicked Allow. Completes the mount; then verify with colab_drive_status. cancel=true abandons a pending mount.

Step 1 of mounting Google Drive on a session: opens Google's approval page in the user's browser. The link itself is NOT returned (it contains the account e-mail) unless the browser could not be opened or show_link=true. The USER must click Allow; never ask for or handle passwords or codes. WARNING: once mounted, code running on the VM can reach the user's WHOLE Drive; mount only when asked, and stop the session afterwards. Then call colab_drive_mount_finish.

Create (if missing) and return a project folder on the mounted Drive: /content/drive/MyDrive/<projects folder>/<name>. Use it for big datasets, checkpoints and results that must survive the session. Requires Drive to be mounted (see colab_drive_status).

Is Google Drive mounted on this session? Reports yes/no and free space only (never lists your files). If it is not mounted, use colab_drive_mount_start (the user approves in the browser).

Make sure a named session exists: reuse it if `colab status` finds it, otherwise create it. Safe to call repeatedly.

Run Python on the runtime; variables persist between calls (same kernel). Give `code` (text) or `file` (local .py/.ipynb inside the working directory), not both. A .ipynb `file` runs the whole notebook and the CLI writes '<name>_output.ipynb' beside it; for cell-by-cell work use the colab_notebook_* tools. `secrets`: NAMES of variables from the user's secrets file (e.g. ["OPENROUTER_API_KEY"]); they become environment variables in the kernel and their values are never returned. `plot_path`: local path (inside the working directory) where a displayed image is saved. `timeout`: seconds (the CLI default is 30).

Install Python packages on the runtime (uses uv, falls back to pip). Names/specifiers only, e.g. 'qiskit', 'pandas>=2.0'.

Terminate a running background job (SIGTERM to its process group).

List all background jobs started on this VM.

Last `tail` lines of a background job's combined stdout/stderr, plus its state.

Start a shell command in the background on the VM (e.g. 'python -u train.py --epochs 50') and return a job id. Use for anything longer than a few minutes; poll with colab_job_status / colab_job_logs. Jobs die if the VM is stopped.

State of a background job: running, finished (with exit code), cancelled, or lost.

Delete everything this tool keeps only temporarily on your computer: transfer zips, saved plots and old local trash. Never touches your notebooks, data or anything outside those folders.

Show how much this tool keeps on your computer (temp files, plots, local trash), free disk and the working-directory budget. Read-only.

Last `lines` entries of a session's history (event_type e.g. execution, file_operation). Without a session, lists sessions that have logs.

List files in a VM directory (default /content).

Create a runtime. CPU by default; gpu: T4, L4, G4, H100 or A100; tpu: v5e1 or v6e1; high_mem needs Colab Pro. Consumes compute units until stopped.

Insert a cell. Default is at the end; or give `position` (index) or `after` (cell id/index). cell_type: code or markdown.

Clear saved outputs of one cell, or of all cells.

Create a local .ipynb inside the working directory. `cells`: list of {"type": "code"|"markdown", "source": "..."}.

Delete a local notebook by moving it to .colab-mcp-trash/ inside the working directory (recoverable, never a hard delete).

Delete one cell by id or index.

Replace a cell's source (and optionally its type). `cell` is an id or an index. Clears that cell's stale outputs.

List .ipynb files under a directory of the working directory.

Move a cell to a new index.

Show a notebook's cells (index, id, type, source) and, optionally, their saved outputs. Use `start`/`end` to page through big notebooks.

Run every code cell in order (from index `start`), storing outputs in the notebook. Stops at the first failing cell unless stop_on_error=false.

Run ONE code cell on the runtime (state persists between cells) and store its output in the notebook. Reports ok/ERROR status. A displayed plot is saved under .colab-mcp/images/.

Convert a notebook to a .py script (markdown becomes comments; lines starting with ! or % are commented out). With `out_path`, writes the file; otherwise returns the text. Handy before colab_run.

Restart the Jupyter kernel of a session: clears all Python variables but keeps the VM and its files.

Delete ONE file on the VM (not on the user's computer). Refuses root-like paths.

One-shot job: allocate a fresh VM, run a local script (inside the working directory) with `args`, then release the VM (or keep it with keep=true).

Report the VM's Python version, CPUs, RAM, free disk and GPU (if any).

List active Colab runtimes (sessions). Also a quick check that Google sign-in works.

Show hardware, machine shape and state of a session (or the only active one).

Stop a session and release the VM (stops consuming compute units). Files not downloaded are lost.

Upload one local file (inside the working directory) to the VM, e.g. remote_path '/content/data.csv'. Limited by COLAB_MCP_MAX_UPLOAD_MB (default 100): for big data, download it on the VM instead (colab_exec / colab_job_start).

Upload a whole local folder (inside the working directory) to the VM as one zip, extracted at `remote_dir`. Skips .git, caches, symlinks and likely secret files (.env, *.key, *.pem...).

Print the browser URL that attaches the Colab UI to this session (does not open a browser).

Show the account's compute-unit balance and current burn rate.