$ loading_
Monitor NVIDIA GPU utilization, memory, temperature, and power with MIG support.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "GPU MCP Server" yet — see the docs or source repo.
Read utilization, memory usage, temperature, and power for all NVIDIA GPUs on the current server, and organize the results in a table by GPU ID.
A monitoring table summarizing key metrics for each GPU by ID.
List the MIG instances on this machine and their GPU resource usage, including memory consumption and utilization, and flag unusually high instances.
An instance-level MIG resource usage report highlighting potentially abnormal instances.
Check temperature and power draw for all GPUs, identify devices exceeding safe thresholds, and provide brief alert notes.
An alert report listing abnormal GPUs and the reasons they exceeded thresholds.
Lets AI check live system metrics and monitor performance thresholds.
Track AI usage, costs, logs, and debug model interactions across apps.
Manage GPU inventory, VM lifecycle, billing, SSH keys, and setup recipes.
Query real-time and historical server metrics from Prometheus for monitoring and troubleshooting.
Access NVIDIA-hosted LLM chat, model discovery, and image generation APIs.
Call tools like weather lookup via MCP with reusable resources and prompts.