GPU Server

Wraps NVIDIA GPU metrics into MCP tools so you can ask Claude about GPU status instead of ssh-ing in to run nvidia-smi. Exposes five tools: gpu_info for driver and CUDA version, gpu_utilization for core and memory bandwidth percentages, gpu_vram for memory stats, gpu_temperature for thermals, and gpu_stats for everything at once. Uses pynvml directly when available, falls back to nvidia-smi subprocess otherwise. Returns clean JSON either way. Useful if you're training models on remote boxes and want to check VRAM or utilization without leaving your conversation. Requires Python 3.10+ and NVIDIA drivers on the host.