Google Colab is a free cloud-based platform that allows users to write and execute Python code through a browser, particularly for machine learning, data analysis, and education. It provides access to GPU and TPU computing resources.
Enables AI agents to use Google Colab end to end: create and stop GPU/TPU runtimes, run code in persistent kernels, work with local .ipynb notebooks cell by cell, launch long-running background jobs, and move files and folders to and from the Colab VM via the official Colab CLI.
Enables AI agents to drive Google Colab end to end through Google's official Colab CLI: creating and stopping GPU/TPU runtimes, executing code, editing local notebooks cell by cell, launching long background jobs, and uploading or downloading files and folders. Optionally adds opt-in Google Drive tools for signing in, managing project folders, and creating, editing or trashing notebooks, plus mounting Drive on the VM for large datasets.
42
4
Apache 2.0
Why this server?
Controls Google Colab as a development, shell, file, and training runtime, providing tools for notebook editing, runtime management, file transfer, GPU monitoring, and more.
Local-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.
59
8
Apache 2.0
Why this server?
Connects local AI assistants directly to browser-based Google Colab notebooks, enabling execution of Python code and interaction with notebook states.
An 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.
1
Apache 2.0
Why this server?
Allocates Google Colab GPU/TPU runtimes and executes Python code on them, supporting accelerators like T4, L4, A100, H100, G4, and TPUs V5E1, V6E1, with background execution and automatic runtime release.
Enables MCP-compatible AI assistants to run Python code on Google Colab GPU/TPU runtimes, supporting accelerators like T4, A100, H100, with background execution and Google Drive integration.
10
3
MIT
Why this server?
Provides tools for controlling Google Colab notebooks, including adding, editing, running, and deleting cells, as well as managing runtime and GPU assignments.
Enhanced fork of Google's Colab MCP, pre-registers all 7 notebook tools at startup (get_cells, add/run/update/delete/move_cell, add_text_cell), adds programmatic GPU control (T4/L4/A100) via OAuth, and fixes the "Disconnected from local server" issue with IPv4-only bind, PNA CORS headers, and stale-tab dedup. Works on Chrome, Edge, Windows, macOS, Linux.
9
21
Apache 2.0
Why this server?
Prepares and edits notebooks compatible with Google Colab, normalizing Colab-specific metadata during downloads, and providing a URL to open notebooks in Colab.
An MCP server for safely inspecting, editing, and synchronizing Google Colab-compatible .ipynb notebooks through Google Drive.
16
39 PyPI
MIT
Why this server?
Executes Python code on Google Colab GPU runtimes, enabling GPU-accelerated computation such as CUDA, PyTorch, and TensorFlow without local GPU hardware.
MCP 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.
3
9
MIT
Why this server?
Provides tools for interacting with Google Colab runtimes, including starting and stopping sessions, executing commands and notebooks, managing files, transferring data, and inspecting runtime resources.
A Model Context Protocol server that gives Codex and other MCP clients access to Google Colab runtimes—allowing session allocation, command execution, notebook management, file operations, and data transfers.
35
2
Apache 2.0
Why this server?
Allows AI agents to use Google Colab as an execution environment, including running code, managing notebooks, installing packages, inspecting GPU/CPU/RAM, running training jobs, and managing files and artifacts.
Lets any MCP-compatible agent use Google Colab or Jupyter runtimes as an execution backend, enabling code execution, notebook management, package installation, hardware introspection, training jobs, and file handling.