MCP.Market

Colab-MCP (unofficial) MCP server

by amgallego8·io.github.amgallego8/colab-mcp·v0.1.0·2 stars
No reviews yet

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

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
New

2 stars

Reviews

Write one

Nobody has reviewed Colab-MCP (unofficial) yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Colab-MCP (unofficial) tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings
  • Code scan10 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Colab-MCP (unofficial) compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
GitHub stars
2
more than 75% of 28,688 servers

Install Colab-MCP (unofficial) in Claude Code, Cursor or VS Code

claude mcp add colab-mcp -- uvx colab-cli-mcp
Add to Cursor

What the publisher says

From the Colab-MCP (unofficial) repository's README, as published. We do not edit it. Read it on GitHub

Colab-MCP

<!-- mcp-name: io.github.amgallego8/colab-mcp -->

An MCP server that lets an AI agent (Claude, or any MCP client) use Google Colab end to end: create and stop GPU/TPU runtimes, run code, work in notebooks cell by cell, launch long background jobs, and move files and folders in and out of the VM.

It is a thin, safe layer over Google's official Colab CLI (google-colab-cli). It does not reimplement Colab and does not depend on a browser tab.

🇪🇸 Resumen en español al final de este archivo.

Quick start

You need uv and the official Colab CLI, signed in once (macOS or Linux):

uv tool install google-colab-cli
colab sessions        # sign in ONCE (open the link, paste the code)
claude mcp add colab-cli -e COLAB_MCP_WORKDIR="$HOME/colab-work" -- uvx colab-cli-mcp

That registers the server in Claude Code, and uvx downloads it from PyPI the first time. For Claude Desktop, other clients, secrets and the optional Drive tools, see Install.

Status

  • Tested against a simulated CLI (118 checks, plus 129 for Drive against a simulated Drive API, 28 for the Drive mount and 17 for local cleanup; tests/): a real MCP client talks to the server over stdio and the code that normally runs on the VM is executed for real in a sandbox folder.
  • Validated live once. On a real Colab session (macOS, Claude as the client): creating a runtime, running code, a long background job with log polling, mounting Drive from the chat (below) and stopping the session, with one real batch workload (10 items, 0 errors). That is a single run, not a benchmark.
  • Published on PyPI as colab-cli-mcp 0.1.0. The published package was installed in a clean environment (pip, and uvx) and listed its 42 tools over stdio. That check ran on Linux; use of the uvx route with Claude on macOS has not been checked yet.
  • Not yet validated live: the Google Drive API tools (drive), notebook execution cell by cell, folder uploads and downloads, and the behaviours listed under Known unknowns*. Other MCP clients (Cursor, Codex, Windsurf) and Linux are untested.
  • Linux and macOS only (the Colab CLI does not support Windows).

Tools (42 + 8 optional Drive tools)

Typical flows:

  • Interactive: colabensuresession(gpu="T4") → colabnotebookcreate → add cells → colabnotebookruncell one by one (variables persist) → read outputs → colabstop.
  • Batch: colabuploaddir → colabjobstart("python -u train.py") → poll colabjoblogs → colabdownloaddir → colab_stop.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Colab-MCP (unofficial): common questions

Is Colab-MCP (unofficial) MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Colab-MCP (unofficial) safety report
How do I install Colab-MCP (unofficial)?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Colab-MCP (unofficial) need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is Colab-MCP (unofficial) maintained?
The last commit was 19 days ago (2026-10-16). The latest release is v0.1.0.
How does Colab-MCP (unofficial) compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); github stars 2 (more than 75% of 28,688 servers). Full comparison.