# Colab-MCP (unofficial) (pypi · colab-cli-mcp)

Unofficial MCP server for Google Colab: runtimes, code, long jobs, files and notebooks.

- Trust score: 84/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `colab-cli-mcp`: 84/100 (this document), [markdown](https://verifymcp.io/servers/amgallego8-colab-mcp/colab-cli-mcp.md), [page](https://verifymcp.io/servers/amgallego8-colab-mcp/colab-cli-mcp)

## Channel facts

- Registry: `pypi`
- Package: `colab-cli-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 45 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to amgallego8/Colab-MCP).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 20 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2456 tokens (~58/item across 42 items; 42 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 67/100
  - Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 6 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "colab_exec" implies "exec" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 42 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Colab-MCP (unofficial) server?

Colab-MCP (unofficial) runs locally as a PyPI package, launched with uvx colab-cli-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add amgallego8-colab-mcp -- uvx colab-cli-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "amgallego8-colab-mcp": {
      "command": "uvx",
      "args": [
        "colab-cli-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "amgallego8-colab-mcp": {
      "command": "uvx",
      "args": [
        "colab-cli-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add amgallego8-colab-mcp -- uvx colab-cli-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "amgallego8-colab-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "colab-cli-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add amgallego8-colab-mcp --command uvx --arg colab-cli-mcp
```

### Hermes

```yaml
mcp_servers:
  amgallego8-colab-mcp:
    command: "uvx"
    args: ["colab-cli-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "amgallego8-colab-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "colab-cli-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add amgallego8-colab-mcp -t stdio -c uvx -a colab-cli-mcp
```

### Other

```json
{
  "mcpServers": {
    "amgallego8-colab-mcp": {
      "command": "uvx",
      "args": [
        "colab-cli-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 79, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-10-17 (score 75, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-16 (score 60)

First indexed and scored.

## MCP tools (42)

### `colab_sessions` (~28 tokens)

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

Output parameters:

- `result` (string)

### `colab_status` (~31 tokens)

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

Input parameters:

- `session`

Output parameters:

- `result` (string)

### `colab_usage` (~21 tokens)

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

Output parameters:

- `result` (string)

### `colab_new` (~85 tokens)

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.

Input parameters:

- `gpu`
- `high_mem` (boolean)
- `session`
- `tpu`

Output parameters:

- `result` (string)

### `colab_ensure_session` (~64 tokens)

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

Input parameters:

- `gpu`
- `high_mem` (boolean)
- `session` (string, required)
- `tpu`

Output parameters:

- `result` (string)

### `colab_restart_kernel` (~36 tokens)

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

Input parameters:

- `session`

Output parameters:

- `result` (string)

### `colab_url` (~34 tokens)

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

Input parameters:

- `session`

Output parameters:

- `result` (string)

### `colab_runtime_info` (~34 tokens)

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

Input parameters:

- `session`

Output parameters:

- `result` (string)

### `colab_stop` (~34 tokens)

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

Input parameters:

- `session`

Output parameters:

- `result` (string)

### `colab_install` (~57 tokens)

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

Input parameters:

- `packages` (array, required)
- `session`

Output parameters:

- `result` (string)

### `colab_exec` (~195 tokens)

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).

Input parameters:

- `code`
- `file`
- `plot_path`
- `secrets`
- `session`
- `timeout` (number)

Output parameters:

- `result` (string)

### `colab_run` (~83 tokens)

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).

Input parameters:

- `args`
- `gpu`
- `high_mem` (boolean)
- `keep` (boolean)
- `script` (string, required)
- `timeout` (number)

Output parameters:

- `result` (string)

### `colab_job_start` (~87 tokens)

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.

Input parameters:

- `command` (string, required)
- `name`
- `session`

Output parameters:

- `result` (string)

### `colab_job_status` (~42 tokens)

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

Input parameters:

- `job_id` (string, required)
- `session`

Output parameters:

- `result` (string)

### `colab_job_logs` (~49 tokens)

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

Input parameters:

- `job_id` (string, required)
- `session`
- `tail` (integer)

Output parameters:

- `result` (string)

### `colab_job_cancel` (~37 tokens)

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

Input parameters:

- `job_id` (string, required)
- `session`

Output parameters:

- `result` (string)

### `colab_job_list` (~24 tokens)

List all background jobs started on this VM.

Input parameters:

- `session`

Output parameters:

- `result` (string)

### `colab_notebook_create` (~62 tokens)

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

Input parameters:

- `cells`
- `overwrite` (boolean)
- `path` (string, required)

Output parameters:

- `result` (string)

### `colab_notebook_list` (~32 tokens)

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

Input parameters:

- `directory` (string)

Output parameters:

- `result` (string)

### `colab_notebook_read` (~74 tokens)

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

Input parameters:

- `end`
- `include_outputs` (boolean)
- `path` (string, required)
- `start` (integer)

Output parameters:

- `result` (string)

### `colab_notebook_add_cell` (~78 tokens)

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

Input parameters:

- `after`
- `cell_type` (string)
- `path` (string, required)
- `position`
- `source` (string, required)

Output parameters:

- `result` (string)

### `colab_notebook_edit_cell` (~67 tokens)

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

Input parameters:

- `cell` (string, required)
- `cell_type`
- `path` (string, required)
- `source` (string, required)

Output parameters:

- `result` (string)

### `colab_notebook_delete_cell` (~34 tokens)

Delete one cell by id or index.

Input parameters:

- `cell` (string, required)
- `path` (string, required)

Output parameters:

- `result` (string)

### `colab_notebook_move_cell` (~42 tokens)

Move a cell to a new index.

Input parameters:

- `cell` (string, required)
- `path` (string, required)
- `to_index` (integer, required)

Output parameters:

- `result` (string)

### `colab_notebook_clear_outputs` (~36 tokens)

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

Input parameters:

- `cell`
- `path` (string, required)

Output parameters:

- `result` (string)

### `colab_notebook_run_cell` (~78 tokens)

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/.

Input parameters:

- `cell` (string, required)
- `path` (string, required)
- `session`
- `timeout` (number)

Output parameters:

- `result` (string)

### `colab_notebook_run_all` (~80 tokens)

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.

Input parameters:

- `path` (string, required)
- `session`
- `start` (integer)
- `stop_on_error` (boolean)
- `timeout_per_cell` (number)

Output parameters:

- `result` (string)

### `colab_notebook_to_script` (~68 tokens)

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.

Input parameters:

- `out_path`
- `path` (string, required)

Output parameters:

- `result` (string)

### `colab_notebook_delete` (~46 tokens)

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

Input parameters:

- `path` (string, required)

Output parameters:

- `result` (string)

### `colab_upload` (~88 tokens)

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).

Input parameters:

- `local_path` (string, required)
- `remote_path` (string, required)
- `session`

Output parameters:

- `result` (string)

### `colab_download` (~41 tokens)

Download one file from the VM into the working directory.

Input parameters:

- `local_path` (string, required)
- `remote_path` (string, required)
- `session`

Output parameters:

- `result` (string)

### `colab_upload_dir` (~79 tokens)

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...).

Input parameters:

- `local_dir` (string, required)
- `remote_dir` (string, required)
- `session`

Output parameters:

- `result` (string)

### `colab_download_dir` (~74 tokens)

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).

Input parameters:

- `local_dir` (string, required)
- `remote_dir` (string, required)
- `session`

Output parameters:

- `result` (string)

### `colab_ls` (~32 tokens)

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

Input parameters:

- `path` (string)
- `session`

Output parameters:

- `result` (string)

### `colab_rm` (~40 tokens)

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

Input parameters:

- `path` (string, required)
- `session`

Output parameters:

- `result` (string)

### `colab_drive_status` (~56 tokens)

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).

Input parameters:

- `session`

Output parameters:

- `result` (string)

### `colab_drive_mount_start` (~124 tokens)

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.

Input parameters:

- `session` (string, required)
- `show_link` (boolean)

Output parameters:

- `result` (string)

### `colab_drive_mount_finish` (~64 tokens)

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.

Input parameters:

- `cancel` (boolean)
- `session` (string, required)

Output parameters:

- `result` (string)

### `colab_drive_project_dir` (~77 tokens)

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).

Input parameters:

- `name` (string, required)
- `session`

Output parameters:

- `result` (string)

### `colab_log` (~58 tokens)

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

Input parameters:

- `event_type`
- `lines` (integer)
- `session`

Output parameters:

- `result` (string)

### `colab_local_footprint` (~41 tokens)

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

Output parameters:

- `result` (string)

### `colab_local_cleanup` (~44 tokens)

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.

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/amgallego8-colab-mcp/colab-cli-mcp#diagnostics

## Score history

- 2026-11-05: 84
- 2026-11-04: 84
- 2026-11-03: 83
- 2026-11-02: 83
- 2026-11-01: 82
- 2026-10-31: 82
- 2026-10-30: 82
- 2026-10-29: 81
- 2026-10-28: 81
- 2026-10-27: 80
- 2026-10-26: 80
- 2026-10-25: 79
- 2026-10-24: 79
- 2026-10-23: 75
- 2026-10-22: 75
- 2026-10-21: 75
- 2026-10-20: 75
- 2026-10-19: 75
- 2026-10-18: 75
- 2026-10-17: 75
- 2026-10-16: 60

## Common questions

### What is the Colab-MCP (unofficial) server?

Colab-MCP (unofficial) is listed in the public MCP registry as io.github.amgallego8/colab-mcp. Unofficial MCP server for Google Colab: runtimes, code, long jobs, files and notebooks. This page covers its PyPI package (colab-cli-mcp).

### Is the Colab-MCP (unofficial) server safe to use?

Colab-MCP (unofficial) scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Colab-MCP (unofficial) server expose?

Colab-MCP (unofficial) exposes 42 tools: colab_sessions, colab_status, colab_usage, colab_new, colab_ensure_session, and 37 more. Their descriptions and schemas cost roughly 2,456 tokens of context every time the server is loaded.

### Is the Colab-MCP (unofficial) server still maintained?

Colab-MCP (unofficial) is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Colab-MCP (unofficial) server under?

Colab-MCP (unofficial) declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Colab-MCP (unofficial) server?

VerifyMCP ran 16 checks on Colab-MCP (unofficial), covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/colab-cli-mcp/
- Socket report: https://socket.dev/pypi/package/colab-cli-mcp
- Repository: https://github.com/amgallego8/Colab-MCP
- Changelog RSS feed: https://verifymcp.io/servers/amgallego8-colab-mcp/colab-cli-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/amgallego8-colab-mcp/colab-cli-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/amgallego8-colab-mcp/colab-cli-mcp.json
- HTML version of this page: https://verifymcp.io/servers/amgallego8-colab-mcp/colab-cli-mcp