pmady/gpu-mcp-server
Deployment & DevOps이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기
MCP server for NVIDIA GPU metrics give AI agents real-time access to GPU utilization, memory, temperature, and power
개요
the OpenSSF Best Practices questionnaire is in progress. Once the project entry is registered at https://www.bestpractices.dev/en, 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. All tools support MIG (Multi-Instance GPU) - MIG instances appear as separate devices with their parent GPU's shared metrics (temperature, power, PCIe). 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. get_gpu_metrics (with {"index": 0} or {"uuid": "GPU-aaaa-1111"}): MIG instances add is_mig, parent_gpu, and mig_profile fields to the get_gpu_metrics and list_gpus payloads. Add to .cursor/mcp.json for a project, or ~/.
README
원문 README의 일부입니다. 원문 보기.
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:
[](https://www.bestpractices.dev/projects/)
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
| Tool | Description |
|---|---|
list_gpus |
List all GPUs with utilization and memory info |
get_gpu_metrics |
Detailed metrics for a GPU by index or UUID |
get_gpu_processes |
PID-level GPU process attribution |
gpu_summary |
Aggregate stats across all devices |
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
}
]
}
설치
docker run --rm -i --gpus all ghcr.io/pmady/gpu-mcp-server:latest설정
{
"mcpServers": {
"gpu": {
"command": "/path/to/gpu-mcp-server"
}
}
}