GPU MCP Server

gpu-mcp-server

Note: the OpenSSF Best Practices questionnaire is in progress. Once the

project entry is registered at , swap the

static badge above for the live one:

An MCP server that exposes NVIDIA GPU metrics as tools. Any MCP-compatible AI agent (Claude, Goose, Cursor, etc.) can query real-time GPU utilization, memory, temperature, power, PCIe and NVLink throughput no Prometheus or dcgm-exporter required.

Built on the official Go MCP SDK and NVIDIA go-nvml.

Tools

All tools support MIG (Multi-Instance GPU) - MIG instances appear as separate devices with their parent GPU's shared metrics (temperature, power, PCIe).

Sample output

Each tool returns structured JSON. The examples below show the shape of the data an agent receives from a node with two NVIDIA A100 GPUs.

list_gpus:

{
  "count": 2,
  "devices": [
    {
      "index": 0,
      "uuid": "GPU-aaaa-1111",
      "name": "NVIDIA A100-SXM4-80GB",
      "gpu_utilization_percent": 85,
      "memory_used_mib": 57344,
      "memory_total_mib": 81920
    },
    {
      "index": 1,
      "uuid": "GPU-bbbb-2222",
      "name": "NVIDIA A100-SXM4-80GB",
      "gpu_utilization_percent": 20,
      "memory_used_mib": 12288,
      "memory_total_mib": 81920
    }
  ]
}

getgpumetrics (with {"index": 0} or {"uuid": "GPU-aaaa-1111"}):

{
  "index": 0,
  "uuid": "GPU-aaaa-1111",
  "name": "NVIDIA A100-SXM4-80GB",
  "gpu_utilization_percent": 85,
  "memory_utilization_percent": 70,
  "memory_used_mib": 57344,
  "memory_total_mib": 81920,
  "temperature_celsius": 72,
  "power_draw_watts": 300,
  "power_limit_watts": 400,
  "pcie_tx_kbps": 0,
  "pcie_rx_kbps": 0,
  "nvlink_tx_mbps": 0,
  "nvlink_rx_mbps": 0
}

gpu_summary:

{
  "device_count": 2,
  "avg_gpu_utilization": 52.5,
  "avg_memory_utilization": 42.5,
  "total_memory_used_mib": 69632,
  "total_memory_total_mib": 163840,
  "max_temperature_celsius": 72,
  "total_power_draw_watts": 375
}

MIG instances add ismig, parentgpu, and migprofile fields to the getgpumetrics and listgpus payloads.

Quick start

# build (requires CGO + NVML headers on Linux)
make build

# run the server communicates over stdio
./gpu-mcp-server

Claude Desktop

Add to claudedesktopconfig.json:

Shortened. The full README is on GitHub.