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.
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.
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.
A self-hosted MCP server providing Claude with an interactive Jupyter environment, including real kernels, persistent notebooks, and optional GPU offload to Google Colab.
MCP server for running external coding agents as background tasks inside Claude Code. Supports multiple backends including Codex, Grok, GLM, DeepSeek, and more.