GPU Server MCP Server

by moezdil Your server? Claim it

local only

GPU Server runs on your own machine — the client starts it, so there is no endpoint to ping. 561 installs a week from pypi. Last commit 22 Oct 2026.

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

Installs per day peak 372 · avg 18

a month agotoday

561

Installs / week

pypi · gpu-server

Stars

0 open issues

22 Oct 2026

Last commit

from GitHub

—

License

Python

What the code does

We read the source, 3 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command src/mcp_gpu_server/server.py:50

        rows = subprocess.run(

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp-gpu-server -- uvx gpu-server

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-gpu-server": {
      "command": "uvx",
      "args": [
        "gpu-server"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp-gpu-server]
command = "uvx"
args = ["gpu-server"]

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-gpu-server": {
      "command": "uvx",
      "args": [
        "gpu-server"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp-gpu-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "gpu-server"
      ]
    }
  }
}

Alternatives to GPU Server

same job, measured the same way

GPU MCP Server

by pmady

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

local only

Zabbix MCP

by mhajder

MCP server for Zabbix monitoring and automation

1 397 installs/wk local only

MCP Console Automation

by ooples

MCP server for AI-driven console application automation and monitoring

16 installs/wk local only

MCP Server Health Monitor

by dbsectrainer

Health monitoring for all your MCP servers

14 installs/wk local only

ChangeDetection.io MCP Server

by rusty4444

MCP server for ChangeDetection.io website monitoring and change history.

148 installs/wk local only

Ninjaone

by lungshot

MCP server for NinjaONE RMM with device management, monitoring, and automation

local only

UISP

by wyre-ai

MCP server for Ubiquiti UISP's REST API - network/ISP infrastructure monitoring for MSPs.

local only

PRTG

by wyre-ai

MCP server for Paessler PRTG's REST API v2 - network/infrastructure monitoring for MSPs.

local only

GPU Server — questions

Answers built from our own checks of this server.

Why is there no uptime for GPU Server?

GPU Server runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package gpu-server was installed 561 times last week.

How do I connect GPU Server?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls gpu-server straight from pypi; nothing to host, nothing to sign up for.

How many people use GPU Server?

The pypi package gpu-server was installed 561 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is GPU Server open source?

We cannot say either way: written in Python and 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.