프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. 리뷰와 계정 기능은 다음 단계에서 열려요.
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

Colab-MCP (unofficial)

제작자: amgallego8버전 0.1.0i★ –i내 컴퓨터에서 실행
레지스트리 이름io.github.amgallego8/colab-mcp

설치

개요

제작자가 쓴 설명(영어 원문)

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

PopNx MCP의 세 기둥

이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.

할 수 있는 일

이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.

  • 연결 방식: 내 컴퓨터에서 실행
  • 전송 방식: stdio
  • 카테고리: 문서, 시트 및 사무 업무

설치

쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.

설치하기 전에

  • 기본 점검: 1개 중 1개 통과
  • 내 컴퓨터에서 내 사용자 계정의 권한(파일, 네트워크, 앱)으로 실행돼요.
  • 직접 입력할 값: COLAB_MCP_WORKDIR, COLAB_MCP_DRIVE

필요한 것

  • PyPIPython의 uv 설치(uvx 명령어용)

어떤 앱을 쓰세요?

위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.

Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요

{
  "mcpServers": {
    "colab": {
      "command": "uvx",
      "args": [
        "colab-cli-mcp"
      ],
      "env": {
        "COLAB_MCP_WORKDIR": "your-value",
        "COLAB_MCP_DRIVE": "your-value"
      }
    }
  }
}

터미널에서 이 명령어를 실행하세요

claude mcp add colab --env COLAB_MCP_WORKDIR=your-value --env COLAB_MCP_DRIVE=your-value -- uvx colab-cli-mcp

실행하기 전에 빈 값을 채워 주세요.

Cursor에서 열기

또는 설정을 직접 복사하기

프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요

{
  "mcpServers": {
    "colab": {
      "command": "uvx",
      "args": [
        "colab-cli-mcp"
      ],
      "env": {
        "COLAB_MCP_WORKDIR": "your-value",
        "COLAB_MCP_DRIVE": "your-value"
      }
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

VS Code에서 열기

또는 설정을 직접 복사하기

프로젝트의 .vscode/mcp.json에 붙여 넣으세요

{
  "servers": {
    "colab": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "colab-cli-mcp"
      ],
      "env": {
        "COLAB_MCP_WORKDIR": "your-value",
        "COLAB_MCP_DRIVE": "your-value"
      }
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.

선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.

직접 입력할 값

  • COLAB_MCP_WORKDIR env
    The only local folder the server reads and writes. Defaults to the current directory.
  • COLAB_MCP_DRIVE env
    Set to 1 to enable the optional Google Drive tools (they need a one-time sign-in, see the README).

이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.

할 수 있는 일

내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.

기본 점검i

누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 8일 점검

  • ✓ 통과

    제작자와 저장소 일치

    레지스트리 이름이 GitHub 계정 amgallego8 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요

  • … 아직 점검 안 함

    계속 관리되고 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • … 아직 점검 안 함

    라이선스 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • – 해당 없음

    엔드포인트 응답

    내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요

  • – 해당 없음

    OAuth로 로그인

    내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요

  • … 아직 점검 안 함

    도구 설명에 숨겨진 지시 없음

    내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요

문서, 시트 및 사무 업무 카테고리의 다른 서버와 비교i

  • 이 카테고리의 다른 서버 3583개 중 0%보다 스타가 많아요
  • 이 카테고리의 다른 서버 3583개 중 58%보다 최근에 레지스트리에 공개됐어요
  • 기본 점검 결과가 이 카테고리의 다른 서버 3583개 중 100%와 같거나 더 좋아요

레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.

자주 묻는 질문

Colab-MCP (unofficial), 안전한가요?

해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.

어떤 키나 코드가 필요한가요?

레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.

내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?

내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).

아직 관리되고 있나요?

GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.1.0)은 23일 전 레지스트리에 올라왔어요.

어떤 앱에서 쓸 수 있나요?

Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Python (uv)도 있어야 해요.

대신 쓸 수 있는 건 뭐가 있나요?

같은 카테고리에는: Agent-Native Calendar, Excel MCP Server, MCP Server for Excel

대안

같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.

카드 보는 법:↓ 주간 다운로드i★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i

Agent-Native Calendar

Agent-Native Google Calendar - manage events, sync, and public booking

제작자: BuilderIO성장 중★ 7.6천2개월 전 업데이트

클라우드에서 실행

Excel MCP Server

Create and edit Excel files with AI: charts, PivotTables, formulas. No Excel needed.

제작자: haris-musa널리 사용됨↓ 5만/주★ 4.3천8일 전 업데이트

내 컴퓨터에서 실행

MCP Server for Excel

Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.

제작자: sbroenne성장 중↓ 4.3천/주★ 8475일 전 업데이트

내 컴퓨터에서 실행

제작자의 README

README 열기

제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.

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)

AreaTools
Runtimescolab_new, colab_ensure_session, colab_sessions, colab_status, colab_runtime_info, colab_restart_kernel, colab_url, colab_usage, colab_stop, colab_install
Run codecolab_exec (code or file; kernel state persists between calls), colab_run (one-shot: fresh VM → script → release)
Notebooks (local .ipynb)colab_notebook_create, _list, _read, _add_cell, _edit_cell, _delete_cell, _move_cell, _clear_outputs, _run_cell, _run_all, _to_script, _delete
Long jobscolab_job_start, _status, _logs, _cancel, _list
Filescolab_upload, colab_download, colab_upload_dir, colab_download_dir, colab_ls, colab_rm, colab_log
Drive on the VMcolab_drive_status, colab_drive_mount_start, colab_drive_mount_finish, colab_drive_project_dir (see *Big projects and Drive*)
Local footprintcolab_local_footprint, colab_local_cleanup (see *Where things live*)

Typical flows:

  • Interactive: colab_ensure_session(gpu="T4") → colab_notebook_create → add cells → colab_notebook_run_cell one by one (variables persist) → read outputs → colab_stop.
  • Batch: colab_upload_dir → colab_job_start("python -u train.py") → poll colab_job_logs → colab_download_dir → colab_stop.

Google Drive projects and notebooks are a separate, opt-in feature (below). Deliberately not included anywhere: sign-in through a tool, colab auth, repl, console, ssh, edit. They are interactive and cannot work through a tool call.

Security model

  • Local paths are confined to COLAB_MCP_WORKDIR. ../, absolute paths and symlinks that escape are rejected before anything runs.
  • Secrets never reach the model. COLAB_MCP_ENV_FILE points to a local NAME=value file. The model only passes names (secrets=["OPENROUTER_API_KEY"]); values go to the kernel with --env and are scrubbed from every result. Known limit: while the command runs, the value is visible to other local users in the process list, because the CLI takes it as an argument.
  • No shell. The CLI is run with an argument list. Session names, GPU types, package specifiers and job ids are validated. Everything user-controlled that is embedded in code for the VM goes through repr().
  • Folder transfers are guarded. Uploads skip .git, caches, symlinks and likely secrets (.env, *.pem, *.key…); downloads reject archives with paths that escape the target (zip-slip) or exceed a size limit.
  • No hard deletes on your computer. colab_notebook_delete moves the file to .colab-mcp-trash/. colab_rm only touches the VM and refuses root-like paths.
  • Output is clipped to COLAB_MCP_MAX_OUTPUT characters, and terminal colour codes (tracebacks) are stripped.
  • Code you run executes on Google's machines under your account and spends your compute units. Stop sessions you no longer need.

Big projects and Drive on the VM

For big datasets, checkpoints or results that must survive the session, mount Google Drive on the VM. This is separate from the optional "Drive notebooks" feature below and uses the Colab CLI's own sign-in.

  1. Mount it from the chat, no terminal. colab_drive_mount_start runs the official colab drivemount in a pseudo-terminal (the CLI itself never opens a browser; it only prints a link and waits for Enter), opens Google's approval page in your browser. The link is not repeated in the chat (it contains your account e-mail); it is only returned if the browser could not be opened or with show_link=true. You click Allow (the agent never sees credentials or codes) and tell the agent; colab_drive_mount_finish then sends the Enter the CLI was waiting for and colab_drive_status confirms. Only https://*.google.com links are ever opened, a pending mount is killed after 15 minutes, and there is at most one per session. If you prefer, colab drivemount -s SESSION in a terminal still works. Mounting gives code running on that VM access to your whole Drive (Colab cannot scope it); only mount when you need it and stop the session afterwards.
  2. The agent calls colab_drive_project_dir("my-project"), which creates /content/drive/MyDrive/Colab-MCP/my-project and returns the path. Datasets, checkpoints and outputs go there.
  3. Stop the session when done. Files in that Drive folder remain; everything else on the VM is lost.

Guardrail: the file tools (colab_upload*, colab_download*, colab_ls, colab_rm) refuse any Drive path outside `/content/drive/MyDrive/Colab-MCP/` (folder name configurable with COLAB_MCP_DRIVE_PROJECTS), including .., relative and case tricks. colab_drive_status never lists your files.

Residual risk, stated plainly: once Drive is mounted, *any code that runs on the VM* (colab_exec, colab_run, jobs, notebook cells) can read and change all of your Drive; the path guard only covers this server's file tools, and it cannot see symlinks created on the VM. Mount only when you need it, review the code you run, and stop the session afterwards.

Where things live (and how little stays on your computer)

WhereWhatWhy
The Colab VM disk (about 200 GB free observed on a T4 ⚠️ not guaranteed)Datasets, training, anything heavyFast, free, gone when the session stops
Drive, folder `Colab-MCP/ /`Notebooks and results that must persistSurvives sessions; the only part of Drive this tool can see
Your computerAlmost nothing: a temporary working copy while you edit a notebookAuto-cleaned (below)

Local footprint rules (footprint.py):

  • Transfer zips are removed right after use and swept after 1 hour; saved plots after 2 days (COLAB_MCP_IMAGE_DAYS); locally "deleted" notebooks after 7 days (COLAB_MCP_TRASH_DAYS, 0 = keep); working copies of Drive notebooks after 24 h (COLAB_MCP_DRIVE_COPY_HOURS, 0 = keep) and immediately when you save. The sweep runs when the server starts and on colab_local_cleanup.
  • Only files inside .colab-mcp/ and .colab-mcp-trash/ are ever removed. Symlinks are not followed. Your own notebooks and data are never touched.
  • Guards before downloads: at least COLAB_MCP_MIN_FREE_GB (default 5) must stay free on the disk and the working folder may not exceed COLAB_MCP_WORKDIR_MAX_GB (default 20, 0 = no cap). colab_local_footprint shows the numbers. Keep big data on the VM or in Drive and download only results.

Google Drive: projects and notebooks (opt-in)

Off by default. With COLAB_MCP_DRIVE=1 (the installer sets it when you set Drive up) these tools appear, and only these:

ToolWhat it does
drive_sign_inOpens a browser window on your computer where *you* click Allow. No code or token ever passes through the chat
drive_project_create / drive_project_listOne folder per Colab project inside Colab-MCP. Folders can be created, never deleted or renamed
drive_notebook_createCreates a notebook (empty starter, or a local .ipynb with outputs stripped), optionally inside a project
drive_notebook_listLists the notebooks *this server* created
drive_notebook_open / drive_notebook_saveDownload a notebook to a temporary local copy, edit it with the colab_notebook_* tools, write the content back to the same file. Saving removes the local copy
drive_notebook_deleteMoves one of them to the Drive trash (never permanent)

Layout in your Drive: Colab-MCP/ / .ipynb. The Google permission (drive.file) only reaches files and folders this app created, so your existing "Colab Notebooks" folder and everything else stay invisible to it.

A skill that keeps the agent to exactly this lives in skills/colab-drive-notebooks/SKILL.md: copy that folder to ~/.claude/skills/ (Claude Code) or add it as a skill in your client.

Who is responsible for what

Nobody shares credentials. Each user signs in themselves, and the token lives only on their own disk. You choose once between two OAuth clients (below); this project never sees your token. The model never sees a sign-in link, code or token.

Quick start (every user)

From PyPI:

uvx --from colab-cli-mcp colab-cli-mcp-drive login     # asks once how you want to sign in, remembers it, signs you in

claude mcp add colab-cli -e COLAB_MCP_WORKDIR="$HOME/colab-work" -e COLAB_MCP_DRIVE=1 -- uvx colab-cli-mcp

From a clone of this repository, bash install.sh asks "Set up Drive now?", runs the one-time choice below, and registers the server with the Drive tools enabled. Manually:

git clone https://github.com/amgallego8/Colab-MCP ~/Colab-MCP && cd ~/Colab-MCP

uv sync uv run colab-cli-mcp-drive login # same login, run from the clone

login walks you through creating your own Google Cloud "Desktop app" client (about 10 minutes, once, free; steps below). When you give it the path of the JSON you downloaded it stores it for you (0600). You answer to Google for your project. After that, signing in is just: a link opens in your browser, you click Allow, done. There is no code to paste.

No shared one-click client is shipped yet. If this repository reaches 1,000 stars, the

앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요

PopNx에게 묻기