Directory
‹ Back to apps

CloudGPU MCP

CloudGPU is compute infrastructure for AI agents. Your agent finds GPUs and open models on its own; you sign in with Google once, approve a budget and top up, and it gets the work done.

What’s inside

1 MCP server · 2 skills
  • MCP servercloudgpuMCP server: cloudgpu
  • Skillcloudgpu-model-apiCall a hosted model through CloudGPU's OpenAI-compatible model API at https://cloudgpu.app/v1, without renting a GPU. Use when the user wants to call a hosted model (chat/completions) through CloudGPU, wire CloudGPU into an OpenAI-compatible client or agent framework (OpenAI SDK, LangChain, Cline, Roo Code, Continue, Aider, n8n, Dify), or mentions cloudgpu.app/v1.
  • SkillcloudgpuRent and use a cloud GPU on CloudGPU (cloudgpu.app) through the `cloudgpu` MCP tools. Use when the user wants to rent a GPU, run a training, fine-tuning, inference or ComfyUI job on a cloud GPU, or mentions CloudGPU or cloudgpu.app, and the `cloudgpu` MCP tools are available.