Skip to content
mcp/skillhub

GPU MCP Server

by pmadyio.github.pmady/gpu-mcp-serverv0.1.0

NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.

15Dockerstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active19d ago

Install GPU MCP server

Install in Claude Code

claude mcp add gpu-pmady -- docker run -i --rm ghcr.io/pmady/gpu-mcp-server:v0.1.0

Freshness

Active — last maintenance signal 19d ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-09-21 · 19d ago · GitHub

  2. Latest release

    2026-09-21 · 19d ago · GitHub · v0.2.0

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-06-25 · 4mo ago · official registry · v0.1.0

FAQ

›How do I install the GPU MCP server in Claude Code?

Run: claude mcp add gpu-pmady -- docker run -i --rm ghcr.io/pmady/gpu-mcp-server:v0.1.0. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does GPU require an API key?

No required environment variables are declared in its published metadata.

›Can I use GPU as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is GPU in the official MCP registry?

Yes, as io.github.pmady/gpu-mcp-server.

Alternatives to GPU

Other memory MCP servers.

View all