Skip to content
Agentmart
Submit a tool

GPU Server

MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature

Connector by moezdil · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/moezdil-mcp-gpu-server

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools
2 read · 0 write · 0 delete · 3 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 5

Read from the source code; the running server may list different tools.

Read 2 · Look things up without changing anything.

  • gpu_info
  • gpu_stats

Not yet classified 3 · We could not tell from the name and description.

  • gpu_temperature
  • gpu_utilization
  • gpu_vram

Network hosts it talks to 1

  • github.com · found in code

Tools (5)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • gpu_info

    GPU name, driver version, and highest CUDA version the driver supports, per device. cuda is null when NVML is unavailable (nvidia-smi fallback).

  • gpu_stats

    Full snapshot: info, VRAM, utilization, and temperature for every device. Prefer this over several single-metric calls. count is 0 and error is set when no NVIDIA GPU is found.

  • gpu_temperature

    Core temperature in °C for each device.

  • gpu_utilization

    Busy % of the GPU cores (gpu_pct) and memory controller (mem_pct) for each device. mem_pct is memory bandwidth activity, not how full VRAM is; use gpu_vram for that.

  • gpu_vram

    VRAM total, used, free (MiB) and pct (used/total %) for each device. Use this to check how full VRAM is or whether a model fits.

Signals

Stars
0
Forks
1
Open issues
0
Weekly downloads
225
Last commit
Oct 22, 2026 (6 days ago)
Last release
Oct 21, 2026 (7 days ago)
Last package publish
Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.moezdil/mcp-gpu-server
Version
0.2.2
Auth
No auth
Packages
pypi gpu-server
License
MIT
Repository
github.com/moezdil/mcp-gpu-server
Website
github.com/moezdil/mcp-gpu-server
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

GPU Server MCP server. Agent Mart. https://agentmart.dev/connectors/moezdil-mcp-gpu-server (last updated 2026-10-24)