gpu-mcp-server

pmady/gpu-mcp-server

★ 6 stars Go AI/LLM Updated today

MCP server for NVIDIA GPU metrics give AI agents real-time access to GPU utilization, memory, temperature, and power

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "gpu-mcp-server": {
      "command": "go",
      "args": [
        "run",
        "github.com/pmady/gpu-mcp-server@latest"
      ]
    }
  }
}

README Excerpt

An [MCP](https://modelcontextprotocol.io/) 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](https://github.com/modelcontextprotocol/go-sdk)

Tools (3)

get_gpu_metricsgpu_summarylist_gpus

Topics

aaifai-agentsgolanggpumcpmodel-context-protocolnvidianvml

gpu-mcp-server

Quick Install

README Excerpt

Tools (3)

Topics

Related AI/LLM Servers