Skip to main content
Glama
deeneskoruzh
aerovfx

Colab MCP

by aerovfx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

🪐 Colab MCP (Model Context Protocol)

Python MCP

An MCP (Model Context Protocol) server that seamlessly bridges your local AI agent to a Google Colab session running in your browser.

✨ Features

  • Connects local AI assistants directly to browser-based Colab notebooks

  • Supports executing Python code in Colab via the agent

  • Reads and interacts with Colab notebook states

Related MCP server: colab-mcp

💻 Supported Clients

This MCP server requires a client that supports notifications/tools/list_changed and must be running locally on your device.

Popular clients that meet these criteria include:

🚀 Installation & Setup

  1. Install uv (an extremely fast Python package installer and resolver):

    pip install uv

  2. Configure your MCP Client (e.g., in your mcp.json or equivalent configuration file):

    {
  "mcpServers": {
    "colab-mcp": {
      "command": "uvx",
      "args": ["git+https://github.com/googlecolab/colab-mcp"],
      "timeout": 30000
    }
  }
}

    Note for Googlers (or those with non-standard package indexes): You may need to add --index https://pypi.org/simple to the args array.

💬 Issues & Discussions

We use GitHub Discussions as our primary venue for issue discussion and feature requests.

As discussions mature into clear action items, the maintainers will convert them into tracked issues. This workflow helps us ensure that the issue tracker remains deduplicated, well-understood, and highly actionable.

⚠️ Please do NOT open issues directly.

🤝 Contributing

While we appreciate community interest, we currently do not have the bandwidth to review external contributions. We want to avoid user Pull Requests languishing without review, so we are not accepting external contributions at this time.

If you have a great idea or encounter a pain point, we would love to hear about it on our Discussions page!

🛠️ Internal (For Colab Developers)

Prerequisites

  • uv is required (pip install uv)

  • Configure git hooks to run repository presubmits:

    git config core.hooksPath .githooks

Local Development Setup (Gemini CLI)

To test your local checkout with the Gemini CLI, use this configuration:

{
  "mcpServers": {
    "colab-mcp": {
      "command": "uv",
      "args": ["run", "colab-mcp"],
      "cwd": "/path/to/github/colab-mcp",
      "timeout": 30000
    }
  }
}

MCP_Colab

Available Tools

1 tool
open_colab_browser_connectionA

Opens a connection to a Google Colab browser session and unlocks notebook editing tools. Returns a boolean representing whether the connection attempt succeeded

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the side effect of unlocking editing tools and the boolean return value, but it does not clarify whether the connection is persistent, whether it requires an existing browser session, or whether any side effects beyond unlocking occur.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that conveys the action, the target resource, the functional outcome, and the return type. There is no redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with an output schema, the description is nearly complete: it names the action and return value. The main gap is the lack of any prerequisite or failure-context information, such as requiring an active Colab browser session or what happens if the connection attempt fails.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema provides no parameter semantics to clarify. The description does not need to add parameter meaning, and it appropriately focuses on the operation and return value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Opens') and names a clear resource ('a Google Colab browser session'), and also states the expected outcome ('unlocks notebook editing tools'). With no sibling tools to differentiate, this fully communicates what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used when a Colab browser connection is needed, but it does not state explicit when-to-use guidance, prerequisites, or alternatives. Since there are no sibling tools, the lack of exclusions is acceptable, but contextual guidance is minimal.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.1
    • First observedopen_colab_browser_connection
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation1/5

Only one tool exists, so no ambiguity between tools, but the dimension assesses whether tools can be told apart; with one tool there is no need for disambiguation, but it cannot be 'clearly distinct' from others since there are none.

Naming Consistency3/5

With a single tool, naming consistency is not applicable; however, the name is descriptive and follows a reasonable pattern, so a neutral score is given.

Tool Count2/5

A single tool seems too few for a server named 'Colab MCP', which suggests a broader purpose. The tool only handles opening a connection, leaving other expected functionalities uncovered.

Completeness1/5

The server's domain appears to be Google Colab integration, but only one tool for opening a connection is provided. Missing tools for editing, running cells, managing notebooks, etc., make the surface severely incomplete.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers