Summary
Wraps NVIDIA GPU metrics into MCP tools so you can ask Claude about GPU status instead of ssh-ing in to run nvidia-smi. Exposes five tools: gpu_info for driver and CUDA version, gpu_utilization for core and memory bandwidth percentages, gpu_vram for memory stats, gpu_temperature for thermals, and gpu_stats for everything at once. Uses pynvml directly when available, falls back to nvidia-smi subprocess otherwise. Returns clean JSON either way. Useful if you're training models on remote boxes and want to check VRAM or utilization without leaving your conversation. Requires Python 3.10+ and NVIDIA drivers on the host.
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →mcp-name: io.github.mesutoezdil/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 bandwidth %
gpu_vram total, used, free VRAM in MiB and usage %
gpu_temperature GPU core temperature in Celsius
gpu_stats everything above in one call
Example 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
}
}]
}
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.
Install
pip install mcp-gpu-server
Connect to your MCP client
Add this to your MCP client config file:
{
"mcpServers": {
"gpu": {
"command": "mcp-gpu-server"
}
}
}
Run tests
python tests/test_gpu.py
Requirements
Python 3.10 or higher. NVIDIA GPU with drivers installed on the host machine.
Featured
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →