colab-mcp
Provides tools for interacting with Google Colab, enabling management of notebooks, code execution, and environment configuration.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@colab-mcp Create a Colab notebook and print 'hello world'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Colab-mcp
An MCP server for interacting with Colab.
Setup
Install
uv(pip install uv)Configure for usage (eg for mcp.json style services):
...
"mcpServers": {
"colab-mcp": {
"command": "uvx",
"args": ["git+https://github.com/googlecolab/colab-mcp"],
"timeout": 30000
}
}
...(If you have a non-standard default package index (Googlers), you may also need to add --index https://pypi.org/simple)
Issues & Discussions
We are using GitHub discussions as the place for issue discussion and feature requests. As discussions mature into action items, we will add those items as issues. This helps us ensure that issues in the issue tracker are well-understood, deduplicated, and actionable. For these reasons, please do NOT open issues directly.
Related MCP server: colab-mcp
Internal - For Colab Developers
Prerequisites
uvis required (pip install uv)Configure git hooks to run repo presubmits
git config core.hooksPath .githooksGemini CLI setup
...
"mcpServers": {
"colab-mcp": {
"command": "uv",
"args": ["run", "colab-mcp"],
"cwd": "/path/to/github/colab-mcp",
"timeout": 30000
}
}
...Available Tools
1 toolopen_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
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or misselection. The tool's purpose is clearly stated and no other tools exist to overlap with it.
The single tool name follows a clear verb_noun pattern (open + colab_browser_connection). There are no other tools to introduce naming inconsistencies, so the naming is internally consistent.
A single tool is too few for a server named colab-mcp, especially since the tool description mentions unlocking notebook editing tools that are not actually exposed. The count is at the lower boundary of what could be acceptable for a narrowly scoped connection tool, but it feels too thin for the apparent domain.
The tool surface is severely incomplete: it offers only an initial connection step while the description claims to unlock notebook editing tools that are absent. There are no tools for creating, editing, or executing notebooks, leaving agents with a dead end after establishing the connection.
Maintenance
Related MCP Connectors
An MCP server for deep research or task groups
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server that bridges local AI agents to Google Colab notebooks, enabling execution of Python code and interaction with notebook states directly from the agent.1Apache 2.0
- AlicenseBqualityDmaintenanceLocal-first MCP server for controlling Google Colab as a development, shell, file, and training runtime, with tools for notebook editing, GPU acceleration, and file transfer.599Apache 2.0
- AlicenseBqualityCmaintenanceAn MCP server for safely inspecting, editing, and synchronizing Google Colab-compatible .ipynb notebooks through Google Drive.1628 PyPIMIT
- AlicenseAqualityDmaintenanceMCP server that allocates Google Colab GPU runtimes (T4/L4) and executes Python code on them. Lets any MCP-compatible AI assistant run GPU-accelerated code without local GPU hardware.39MIT