Announcing the Colab MCP Server: Connect Any AI Agent to Google Colab

Source: Google Developers Blog

When you’re prototyping locally with AI agents like Gemini CLI, Claude Code, or your own agent, their potential is often bottlenecked by your local machine. Waiting for agents to scaffold projects or install dependencies slows you down, and letting an autonomous agent run code directly on your hardware may not be ideal.

You need a fast, secure sandbox with powerful compute. By connecting any MCP‑compatible agent to Google Colab, we bridge your local workflow with Colab’s cloud environment.

Starting today, we are releasing the new, open‑source Colab MCP (Model Context Protocol) Server, opening up Google Colab to be accessed directly by any AI agent. This isn’t about a new UI or a different way to share notebooks—it’s about programmatic access to Colab’s native development features. By establishing Colab as an open, extensible host, you can now treat Colab as an automated workspace for any MCP‑compatible agent.

Colab Notebooks as a Tool

We are going beyond just running code in the background; we are giving any agent the ability to natively control the Colab notebook interface. This allows your agent of choice to automate the entire notebook development lifecycle. If you ask an agent to “create a data analysis of this dataset,” it can now programmatically:

• Add and structure cells: Create new .ipynb files and inject markdown cells to explain its methodology.
• Write and execute code: Draft Python cells to load libraries like pandas and matplotlib, and execute them in real time.
• Move and organize content: Rearrange cells to build a logical, readable flow for your final report.
• Manage dependencies: Install necessary libraries (!pip install …) that aren’t in the base image.

This effectively turns Colab into a high‑velocity prototyping sandbox. You receive a fully reproducible, executable artifact that lives in the cloud, built right before your eyes. You can jump into the notebook at any point to inspect the state or take over manually.

How to Install and Get Started

To add the Colab MCP server to your local environment, you just need to configure your agent. The following prerequisites must be installed on your system:

• Python
• Git
• uv (Python package manager)

Install Git

Most macOS and Linux systems already have Git installed. Verify with:

git version

If Git is not installed, follow the instructions at the official guide: .

Install Python

Check for Python with:

python --version

If Python is missing, see the getting‑started page: .

Install uv

The tool requires the Python package manager uv. Install it via pip:

pip install uv

MCP JSON config for the frontend

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

See It in Action

Once your setup is complete, using the MCP server is seamless. Open any Google Colab notebook in your browser and give your local agent a command, for example:

“Load the sales dataset and help me forecast and visualize sales for the next month.”

Your agent will automatically create cells, write and execute the Python code, generate visualizations, and format the analysis live inside the Colab notebook.

We Want Your Feedback!

We built this because developers often copy code from terminals into Colab cells to debug or visualize data—a context switch that kills flow. By treating Colab as a service, we remove the friction between your local development environment and cloud compute.

Since this is a brand‑new way to interact with Colab, we need your help to shape its future. Please try installing the Colab MCP Server with your favorite agent, test its limits, and share your feedback on our GitHub issues page. The project is open source, so community contributions and direct code improvements are welcome. Your input will help drive what we build next!