# gpu-mcp-server

> gpu-mcp-server — pmady-gpu-mcp-server. Use this tool when you need to monitor NVIDIA GPU performance in real-time, solving issues with resource utilization and optimization. It provides AI agents with query functionality for metrics like utilization, memory, temperature, and power, offering a streamlined interface for inputting queries and outputting detailed GPU metrics. Ideal for use cases requiring precise GPU monitoring without relying on external tools.

Canonical page: https://skillsregistry.net/skills/pmady-gpu-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/pmady-gpu-mcp-server

## Description

An MCP server that enables AI agents to query real-time NVIDIA GPU metrics like utilization, memory, temperature, and power without external monitoring tools.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/qu4p1l3nqd)
- **Repository:** <https://github.com/pmady/gpu-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "pmady-gpu-mcp-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pmady-gpu-mcp-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pmady-gpu-mcp-server/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt