# claude-rocm-mcp

> Use this tool when you need to monitor AMD GPU performance and utilization on Linux systems, solving issues with resource allocation and ML process management. It provides read-only access to key metrics such as VRAM, temperature, clocks, power, and running ML processes through the rocm-smi interface. This tool is ideal for optimizing and troubleshooting GPU-intensive workloads, especially those involving machine learning applications.

Canonical page: https://skillsregistry.net/skills/lukelamb-claude-rocm-mcp  
JSON: https://api.skillsregistry.net/v1/skills/lukelamb-claude-rocm-mcp

## Description

Read-only AMD GPU monitoring for Claude on Linux — VRAM, temperature, clocks, power, and running ML processes via rocm-smi.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-09-02

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/te2fbatpgg)
- **Repository:** <https://github.com/LukeLamb/claude-rocm-mcp>

## 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": "lukelamb-claude-rocm-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lukelamb-claude-rocm-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lukelamb-claude-rocm-mcp/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