mcp-gpu-server
This MCP server exposes read-only NVIDIA GPU monitoring tools for MCP-compatible clients.
Get GPU name, driver version, and CUDA version (
gpu_info).Query GPU core and memory utilization percentages (
gpu_utilization).Check total, used, and free VRAM in MiB plus usage percent (
gpu_vram).Read GPU core temperature in Celsius (
gpu_temperature).Retrieve a full snapshot combining info, VRAM, utilization, and temperature (
gpu_stats).All tools take no arguments and return structured JSON; queries use NVML with an nvidia-smi fallback.
Provides tools for querying NVIDIA GPU metrics such as name, utilization, VRAM, and temperature.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-gpu-server what are my GPU metrics?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-name: io.github.moezdil/mcp-gpu-server
mcp-gpu-server
An MCP server that exposes NVIDIA GPU metrics as tools. Once connected, any MCP-compatible client can query your GPU status in real time directly from a conversation.
What it does
Instead of running nvidia-smi manually, you ask your AI assistant and it calls these tools automatically:
gpu_info GPU name, driver version, CUDA version
gpu_utilization core utilization % and memory controller busy %
gpu_vram total, used, free VRAM in MiB and usage %
gpu_temperature GPU core temperature in Celsius
gpu_stats everything above in one callExample response from gpu_stats:
{
"count": 1,
"gpus": [{
"index": 0,
"name": "NVIDIA L40S",
"driver": "580.126.09",
"cuda": "13.0",
"temp_c": 29,
"gpu_pct": 0,
"mem_pct": 0,
"vram": {
"total_mib": 46068,
"used_mib": 610,
"free_mib": 45457,
"pct": 1.3
}
}]
}Related MCP server: gpu-mcp-server
How it works
Queries NVML (pynvml) directly when available. Falls back to nvidia-smi subprocess if NVML is not accessible. Returns clean JSON in both cases. The nvidia-smi query does not include the CUDA version, so cuda is null on that path.
Install
pip install gpu-serverThe package moved from mcp-gpu-server to gpu-server on PyPI in 0.2.1. The old name is frozen at 0.1.3, which does not start with mcp 2.x. The mcp-gpu-server command still works, and since 0.2.2 gpu-server does too.
Listed on the official MCP Registry as io.github.moezdil/mcp-gpu-server.
Connect to your MCP client
Add this to your MCP client config file:
{
"mcpServers": {
"gpu": {
"command": "mcp-gpu-server"
}
}
}Or without installing anything, using uv:
{
"mcpServers": {
"gpu": {
"command": "uvx",
"args": ["gpu-server"]
}
}
}Run tests
uv run pytest tests/test_server.py # no GPU needed
uv run python tests/test_gpu.py # on a GPU hostTested on real hardware
Release 0.2.2 was installed from PyPI into a clean virtual environment on a Linux host and tested against a real GPU on 2026-10-21.
GPU | NVIDIA GeForce RTX 3090, 24 GB |
Driver / CUDA | 580.178.04 / 13.0 |
Python | 3.14.4 |
Packages | gpu-server 0.2.2, mcp 2.3.0, nvidia-ml-py 13.615.71 |
Install the published package and run the GPU integration test:
python3 -m venv venv
venv/bin/pip install gpu-server==0.2.2
git clone --depth 1 https://github.com/moezdil/mcp-gpu-server.git repo
venv/bin/python repo/tests/test_gpu.pyResult: all 37 checks passed. They exercise the NVML path; the nvidia-smi fallback is only checked for presence, not parsed.
Then call every tool through a real MCP client over stdio:
import anyio, json, sys
from mcp import Client, StdioServerParameters
async def main():
async with Client(StdioServerParameters(command=sys.argv[1])) as c:
print("protocol:", c.protocol_version)
for t in (await c.list_tools()).tools:
r = await c.call_tool(t.name, {})
print(t.name, t.annotations.read_only_hint, json.dumps(r.structured_content))
anyio.run(main)Saved as e2e.py and run with venv/bin/python e2e.py venv/bin/gpu-server. Result: the client and server negotiated protocol 2026-07-28, all five tools are listed as read-only, and every call returned structured content without errors:
gpu_stats {"count": 1, "gpus": [{"index": 0, "name": "NVIDIA GeForce RTX 3090",
"driver": "580.178.04", "cuda": "13.0", "temp_c": 42, "gpu_pct": 0, "mem_pct": 0,
"vram": {"total_mib": 24576, "used_mib": 451, "free_mib": 24124, "pct": 1.8}}]}Requirements
Python 3.10 or higher, MCP Python SDK 2.x. NVIDIA GPU with drivers installed on the host machine.
Links
MCP Registry entry: https://registry.modelcontextprotocol.io/v0/servers?search=io.github.moezdil/mcp-gpu-server
Model Context Protocol: https://modelcontextprotocol.io
MCP Python SDK: https://github.com/modelcontextprotocol/python-sdk
NVML (nvidia-ml-py): https://pypi.org/project/nvidia-ml-py/
Available Tools
5 toolsgpu_infoB
GPU name, driver version, and CUDA version for each device.
Inputs: no named parameters. Returns: object
gpu_statsA
Full snapshot: info, VRAM, utilization, and temperature for every device.
Inputs: no named parameters. Returns: object
gpu_temperatureB
Core temperature in °C for each device.
Inputs: no named parameters. Returns: object
gpu_utilizationA
GPU core and memory utilization percentage for each device.
Inputs: no named parameters. Returns: object
gpu_vramA
VRAM total, used, free (MiB) and utilization % for each device.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Tools are mostly distinct, but 'gpu_info' and 'gpu_stats' overlap somewhat as stats includes info content. However, descriptions clarify the difference (basic vs. full snapshot). The other three tools are clearly separate.
All tool names follow a consistent 'gpu_<noun>' pattern in snake_case. The nouns (info, stats, temperature, utilization, vram) are descriptive and predictable.
Five tools is an appropriate scope for a GPU monitoring server. Each tool covers a distinct aspect without unnecessary redundancy, and the count is not overwhelming.
The tool set covers the main GPU monitoring needs: basic info, comprehensive stats, temperature, utilization, and VRAM. Minor gaps like power usage or process listing are absent but not critical for common use cases.
Maintenance
Related MCP Connectors
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceExposes MCP tools that enable remote LLMs to query local Docker containers, OS processes, and system services in real time.-
- AlicenseNot gradedqualityBmaintenanceAn MCP server that enables AI agents to query real-time NVIDIA GPU metrics like utilization, memory, temperature, and power without external monitoring tools.15Apache 2.0
- AlicenseAqualityCmaintenanceEnables AI agents to retrieve live GPU rental prices, compare models, and access market summaries and historical price data through four read-only MCP tools.4MIT
- AlicenseNot gradedqualityBmaintenanceEnables an AI assistant to query local AI stack status, incidents, logs, GPU metrics, and service history, and to trigger restarts through MCP tools.MIT