Puter MCP
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
Runs in the cloud✓ service owner · puter.com
Colab-MCP (unofficial)
What it does
Unofficial MCP server for Google Colab: runtimes, code, long jobs, files and notebooks.
- Connects Runs on your computer
- Account or key No key needed
- Category Docs, sheets & office work
Install
Pick the AI app you use, then copy the settings.
Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 14, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
Install Python (uv)
One time only; it works for every server that needs Python (uv)
Open the Claude desktop app’s settings file
SettingsDeveloperEdit Config
Paste these settings and save the file
{ "mcpServers": { "colab": { "command": "uvx", "args": [ "colab-cli-mcp" ] } } }Quit Claude and open it again
Try it
Use Colab-MCP (unofficial) and tell me what you can do for me, then show me one thing✓ If Claude says it is using Colab-MCP (unofficial) or shows a Colab-MCP (unofficial) tool in the answer, you are connected
2 optional setting(s) (works without them)
The command above works without these. Add them only if you want to change something, following the maker’s description.
COLAB_MCP_WORKDIRThe only local folder the server reads and writes. Defaults to the current directory.COLAB_MCP_DRIVESet to 1 to enable the optional Google Drive tools (they need a one-time sign-in, see the README).
Descriptions are as written by the maker.
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect Colab-MCP (unofficial) yet
Colab-MCP (unofficial) runs on your computer, but ChatGPT can only connect servers that run on the web
What you can do instead
A · Use an app that can connect Colab-MCP (unofficial)
- Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
- Install Python (uv) on your computer first (one time)
- Install Python (uv) on your computer first (one time)
- Install Python (uv) on your computer first (one time)
Works with Claude Code, with some setup first
Install Python (uv) on your computer first (one time)
Install Python (uv)
One time only; it works for every server that needs Python (uv)
Open Terminal
Mac: press Command+Space and type Terminal · Windows: open PowerShell
Paste this command and press Enter
claude mcp add --scope user colab -- uvx colab-cli-mcpType /mcp in Claude Code
You should see Colab-MCP (unofficial) listed as connected
Try it
Use Colab-MCP (unofficial) and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using Colab-MCP (unofficial) or shows a Colab-MCP (unofficial) tool in the answer, you are connected
2 optional setting(s) (works without them)
The command above works without these. Add them only if you want to change something, following the maker’s description.
COLAB_MCP_WORKDIRThe only local folder the server reads and writes. Defaults to the current directory.COLAB_MCP_DRIVESet to 1 to enable the optional Google Drive tools (they need a one-time sign-in, see the README).
Descriptions are as written by the maker.
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor, with some setup first
Install Python (uv) on your computer first (one time)
Install Python (uv)
One time only; it works for every server that needs Python (uv)
Open the AI chat in Cursor in Agent mode
Try it
Use Colab-MCP (unofficial) and tell me what you can do for me, then show me one thing✓ If Cursor says it is using Colab-MCP (unofficial) or shows a Colab-MCP (unofficial) tool in the answer, you are connected
2 optional setting(s) (works without them)
The command above works without these. Add them only if you want to change something, following the maker’s description.
COLAB_MCP_WORKDIRThe only local folder the server reads and writes. Defaults to the current directory.COLAB_MCP_DRIVESet to 1 to enable the optional Google Drive tools (they need a one-time sign-in, see the README).
Descriptions are as written by the maker.
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code, with some setup first
Install Python (uv) on your computer first (one time)
Install Python (uv)
One time only; it works for every server that needs Python (uv)
Open the AI chat in VS Code in Agent mode
Try it
Use Colab-MCP (unofficial) and tell me what you can do for me, then show me one thing✓ If VS Code says it is using Colab-MCP (unofficial) or shows a Colab-MCP (unofficial) tool in the answer, you are connected
2 optional setting(s) (works without them)
The command above works without these. Add them only if you want to change something, following the maker’s description.
COLAB_MCP_WORKDIRThe only local folder the server reads and writes. Defaults to the current directory.COLAB_MCP_DRIVESet to 1 to enable the optional Google Drive tools (they need a one-time sign-in, see the README).
Descriptions are as written by the maker.
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
JSON settings are under “For developers” below
For developers: Terminal commands and JSON settings
Installed on your computer
Claude Code
claude mcp add --scope user colab -- uvx colab-cli-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"colab": {
"command": "uvx",
"args": [
"colab-cli-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"colab": {
"command": "uvx",
"args": [
"colab-cli-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"colab": {
"type": "stdio",
"command": "uvx",
"args": [
"colab-cli-mcp"
]
}
}
}Values you fill in
COLAB_MCP_WORKDIRenvThe only local folder the server reads and writes. Defaults to the current directory.COLAB_MCP_DRIVEenvSet to 1 to enable the optional Google Drive tools (they need a one-time sign-in, see the README).
Descriptions are as written by the maker.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
At a glance
Which apps can use it
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Related guides
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 14, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account amgallego8, which owns the repo
- ✓ Pass
Still maintained
Code last changed 29 days ago
- ✓ Pass
Has a licence
Uses Apache-2.0
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
User reviews
No reviews yet
Compared with others in Docs, sheets & office worki
- More stars than 91% of the other 3927 servers in this category
- Published to the registry more recently than 51% of the other 3927 servers in this category
- Basic checks equal to or better than 100% of the other 3927 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Colab-MCP (unofficial) safe?
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed 29 days ago, and the latest version (0.1.0) reached the registry 29 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
What can I use instead?
In the same category: Puter MCP, XcodeBuildMCP, XcodeBuildMCP
Others in the same category
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
XcodeBuildMCP
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Runs on your computer✓ service owner · xcodebuildmcp.com
XcodeBuildMCP
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Runs on your computer
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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-clicolab 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-mcp0.1.0. The published package was installed in a clean environment (pip, anduvx) and listed its 42 tools over stdio. That check ran on Linux; use of theuvxroute 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)
| Area | Tools |
|---|---|
| Runtimes | colab_new, colab_ensure_session, colab_sessions, colab_status, colab_runtime_info, colab_restart_kernel, colab_url, colab_usage, colab_stop, colab_install |
| Run code | colab_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 jobs | colab_job_start, _status, _logs, _cancel, _list |
| Files | colab_upload, colab_download, colab_upload_dir, colab_download_dir, colab_ls, colab_rm, colab_log |
| Drive on the VM | colab_drive_status, colab_drive_mount_start, colab_drive_mount_finish, colab_drive_project_dir (see *Big projects and Drive*) |
| Local footprint | colab_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_cellone by one (variables persist) → read outputs →colab_stop. - Batch:
colab_upload_dir→colab_job_start("python -u train.py")→ pollcolab_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_FILEpoints to a localNAME=valuefile. The model only passes names (secrets=["OPENROUTER_API_KEY"]); values go to the kernel with--envand 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_deletemoves the file to.colab-mcp-trash/.colab_rmonly touches the VM and refuses root-like paths. - Output is clipped to
COLAB_MCP_MAX_OUTPUTcharacters, 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.
- Mount it from the chat, no terminal.
colab_drive_mount_startruns the officialcolab drivemountin 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 withshow_link=true. You click Allow (the agent never sees credentials or codes) and tell the agent;colab_drive_mount_finishthen sends the Enter the CLI was waiting for andcolab_drive_statusconfirms. Onlyhttps://*.google.comlinks 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 SESSIONin 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. - The agent calls
colab_drive_project_dir("my-project"), which creates/content/drive/MyDrive/Colab-MCP/my-projectand returns the path. Datasets, checkpoints and outputs go there. - 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)
| Where | What | Why |
|---|---|---|
| The Colab VM disk (about 200 GB free observed on a T4 ⚠️ not guaranteed) | Datasets, training, anything heavy | Fast, free, gone when the session stops |
| Drive, folder `Colab-MCP/ /` | Notebooks and results that must persist | Survives sessions; the only part of Drive this tool can see |
| Your computer | Almost nothing: a temporary working copy while you edit a notebook | Auto-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 oncolab_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 exceedCOLAB_MCP_WORKDIR_MAX_GB(default 20,0= no cap).colab_local_footprintshows 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:
| Tool | What it does |
|---|---|
drive_sign_in | Opens a browser window on your computer where *you* click Allow. No code or token ever passes through the chat |
drive_project_create / drive_project_list | One folder per Colab project inside Colab-MCP. Folders can be created, never deleted or renamed |
drive_notebook_create | Creates a notebook (empty starter, or a local .ipynb with outputs stripped), optionally inside a project |
drive_notebook_list | Lists the notebooks *this server* created |
drive_notebook_open / drive_notebook_save | Download 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_delete | Moves 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 inclaude 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-MCPuv 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