GPU MCP Server

An MCP server that exposes NVIDIA GPU metrics as tools. Its 4 documented tools cluster into read & search, gpu.

People who work with aaif, gpu and nvidia and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in HCL.

VERIFIED ACTIVE

LAST COMMIT 2026-09-12 · ★ 15 · #240 OF 304 MAINTAINED MEMORY · VERIFIED 2026-09-18

Apache-2.0 · HCL · how we verify → /methodology

01 · Install GPU MCP Server

Docker

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

Claude Desktop - add to config

{
  "mcpServers": {
    "pmady-gpu-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/pmady/gpu-mcp-server:v0.1.0"
      ]
    }
  }
}

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as container (OCI image) - can be sandboxed away from your filesystem

license Apache-2.0 - declared in the repository

registry namespace io.github.pmady is GitHub-verified and matches the repo owner

03 · What GPU MCP Server can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

An agent gets 4 documented tools across read & search, gpu, including list_gpus, get_gpu_metrics, get_gpu_processes, gpu_summary.

Capability map

Tools grouped from the project's README - what GPU MCP Server lets an agent do.

read & search

3 tools - e.g. List all GPUs with utilization and memory info; Detailed metrics for a GPU by index or UUID; PID-level GPU process attribution

list_gpus · get_gpu_metrics · get_gpu_processes

Gpu

1 tool - e.g. Aggregate stats across all devices

gpu_summary

Latest releases

v0.1.0 · 2026-06-25

Update README.md · New Contributors · @mbrs-afk made their first contribution in

04 · Who maintains GPU MCP Server

GPU MCP Server is maintained by pmady. It's the only MCP server we track from this author; the repo dates to Jun 2026.

05 · Facts

repository: github.com/pmady/gpu-mcp-server
category: memory - ranked #240 of 304 actively-maintained memory servers as of 2026-09-18.
release cadence: 1 release in the last 90 days (latest 2026-06-25)
registry: io.github.pmady/gpu-mcp-server (active, first published 2026-06-25)
packages: oci:ghcr.io/pmady/gpu-mcp-server:v0.1.0

06 · GPU MCP Server FAQ

Is GPU MCP Server still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-12 and it shipped 1 release in the last 90 days. We re-verify nightly.

What can GPU MCP Server do?

An agent gets 4 documented tools across read & search, gpu, including list_gpus, get_gpu_metrics, get_gpu_processes, gpu_summary.

How do I install GPU MCP Server?

Run `docker run -i --rm ghcr.io/pmady/gpu-mcp-server:v0.1.0`. You can also paste the ready-made client config above.

07 · Alternatives to GPU MCP Server

Alternatives to GPU MCP Server

Maintained memory servers if GPU MCP Server isn't the fit.

Pairs well with

Servers that cover what GPU MCP Server doesn't - only shown when the pairing reason fits the companion.

More memory MCP servers · Thread Keeper · Weasley DeepMind · Continuum · Kairn · Lambdacad MCP