Google Colabvf.sr

listing.by · home.legend.verified

Connect a local agent to a Google Colab notebook session open in your browser.

state.local.long (state.local.title)listing.badge.runs_with

listing.install

listing.local.explain

uvx git+https://github.com/googlecolab/colab-mcp

listing.local.needs listing.local.note

act.add_to a11y.new_tabact.add_to a11y.new_tab

listing.share.h

listing.share.p_local

mcp.tc/i/colab

listing.about

Bridges a local AI agent to a Google Colab session running in your browser, so the agent can work with the notebook you have open. The server relies on tool list change notifications, so the set of available tools can update as the session connects.

It runs locally over stdio and is installed from GitHub with uvx, not from PyPI, because the PyPI name colab-mcp belongs to someone else. No API key is needed. The client must run on your own machine and support notifications/tools/list_changed, for example Gemini CLI, Claude Code or Windsurf.

listing.can

  • Bridge a local agent to a Colab session open in the browser
  • Work with a notebook from Gemini CLI, Claude Code or Windsurf
  • Runs locally over stdio with no API key

listing.tools

listing.notools.local

listing.prompts

  • Connect to my open Colab notebook and tell me what it does.

  • Use my Colab session to run this data analysis on the notebook.

  • Add a cell to my Colab notebook that plots the training loss.

listing.setup.h

listing.setup.local

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio colab -- uvx git+https://github.com/googlecolab/colab-mcp
  1. Start Claude Code and type /mcp. colab should show as connected.

Add --scope user to make it available in every project.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "colab": {
      "command": "uvx",
      "args": [
        "git+https://github.com/googlecolab/colab-mcp"
      ]
    }
  }
}
  1. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Add to Cursor a11y.new_tab

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "colab": {
      "command": "uvx",
      "args": [
        "git+https://github.com/googlecolab/colab-mcp"
      ]
    }
  }
}

Needs uv (Python) on your computer.

VS Code

Install in VS Code a11y.new_tab

Or from a terminal:

code --add-mcp '{"name":"colab","type":"stdio","command":"uvx","args":["git+https://github.com/googlecolab/colab-mcp"]}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "colab": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "git+https://github.com/googlecolab/colab-mcp"
      ]
    }
  }
}

Needs uv (Python) on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "colab": {
      "command": "uvx",
      "args": [
        "git+https://github.com/googlecolab/colab-mcp"
      ]
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add colab -- uvx git+https://github.com/googlecolab/colab-mcp

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.colab]
command = "uvx"
args = ["git+https://github.com/googlecolab/colab-mcp"]

Needs uv (Python) on your computer.

Gemini CLI

gemini mcp add colab uvx git+https://github.com/googlecolab/colab-mcp

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "colab": {
      "command": "uvx",
      "args": [
        "git+https://github.com/googlecolab/colab-mcp"
      ]
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs uv (Python) on your computer.

listing.faq

Can I paste mcp.tc/i/colab into my MCP client?

No. Google Colab runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx git+https://github.com/googlecolab/colab-mcp.

Does Google Colab need an API key?

No. It doesn't declare any keys or environment variables. It runs with your user account's permissions, so check what its tools can reach.

Is Google Colab a remote or a local server?

Local. Your client starts it as a process on your computer with uvx git+https://github.com/googlecolab/colab-mcp, which needs uv (Python).

What can Google Colab do?

You can bridge a local agent to a Colab session open in the browser, work with a notebook from Gemini CLI, Claude Code or Windsurf and runs locally over stdio with no API key.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Who wrote this page?

mcp.tc's robot read Google Colab's public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

listing.em.h

listing.em.lead_local listing.em.how

listing.em.badge

em.prev_lightem.prev_dark
Markdown
[![Google Colab on mcp.tc](https://mcp.tc/i/colab/badge.svg)](https://mcp.tc/i/colab)
HTML
<a href="https://mcp.tc/i/colab"><img src="https://mcp.tc/i/colab/badge.svg" alt="Google Colab on mcp.tc" height="20"></a>

listing.em.badge_note

listing.em.widget

HTML
<script src="https://mcp.tc/w/colab.js" async></script>

listing.em.widget_note

iframe

HTML
<iframe src="https://mcp.tc/embed/colab" title="Google Colab on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

listing.em.iframe_note

JSON

listing.em.json_local

https://mcp.tc/i/colab.json

listing.em.fields

listing.related

listing.more_in

  • Jupyter MCP Server

    Datalayer

    state.local.label (state.local.title)

    Read, edit and execute cells in live Jupyter notebooks from your AI assistant.

    mcp.tc/i/jupyter

  • MATLAB

    MathWorks

    state.local.label (state.local.title)

    Run MATLAB code, tests and static code analysis from an AI assistant using a local MATLAB install.

    mcp.tc/i/matlab

  • Nx

    Nx (Nrwl)

    state.local.label (state.local.title)

    Give your AI assistant Nx workspace context: project graph, project details, generators and up-to-date Nx docs.

    mcp.tc/i/nx

  • ROS MCP Server

    robotmcp

    state.local.label (state.local.title)

    Connect LLMs to ROS and ROS 2 robots to work with topics, services, actions and parameters through rosbridge.

    mcp.tc/i/ros

  • Angular CLIvf.sr

    Google (Angular)

    state.local.label (state.local.title)

    Get Angular best practices, documentation search and workspace-aware tools from the Angular CLI inside your assistant.

    mcp.tc/i/angular-cli

  • shadcn/ui

    shadcn

    state.local.label (state.local.title)

    Browse, search and install shadcn/ui components and other registry components into your project from your assistant.

    mcp.tc/i/shadcn

listing.disclaimer_checked