The io.github.pmady/gpu-mcp-server is an MCP server that exposes NVIDIA GPU metrics as tools. It provides access to utilization, memory, temperature, and power, and it supports NVIDIA MIG (Multi-Instance GPU) for partitioned GPU monitoring.

🛠️ Key Features

NVIDIA GPU metrics tooling: utilization, memory, temperature, power
MIG support

🚀 Use Cases

Retrieve real-time GPU performance and health metrics via Model Context Protocol
Monitor partitioned workloads on MIG-enabled NVIDIA hardware

⚡ Developer Benefits

Integrates GPU observability into MCP-based agent or toolchains
Uses established NVIDIA monitoring data fields (utilization, memory, temperature, power)

⚠️ Limitations

Focused on NVIDIA GPU metrics and MIG; does not claim coverage for non-NVIDIA hardware

Topics

aaif, ai-agents, golang, gpu, mcp, model-context-protocol, nvidia, nvml

gpu-mcp-server

DOI OpenSSF Scorecard

Note: the OpenSSF Best Practices questionnaire is in progress. Once the project entry is registered at https://www.bestpractices.dev/en, swap the static badge above for the live one: [![OpenSSF Best Practices](https://www.bestpractices.dev/projects/<ID>/badge)](https://www.bestpractices.dev/projects/<ID>)

An MCP server that exposes NVIDIA GPU metrics as tools. Any MCP-compatible AI agent (Claude, Goose, Cursor, etc.) can query real-time GPU utilization, memory, temperature, power, PCIe and NVLink throughput no Prometheus or dcgm-exporter required.

Built on the official Go MCP SDK and NVIDIA go-nvml.

Tools

Tool	Description
`list_gpus`	List all GPUs with utilization and memory info
`get_gpu_metrics`	Detailed metrics for a GPU by index or UUID
`get_gpu_processes`	PID-level GPU process attribution
`gpu_summary`	Aggregate stats across all devices

All tools support MIG (Multi-Instance GPU) - MIG instances appear as separate devices with their parent GPU's shared metrics (temperature, power, PCIe).

Sample output

Each tool returns structured JSON. The examples below show the shape of the data an agent receives from a node with two NVIDIA A100 GPUs.

list_gpus:

json

{
  "count": 2,
  "devices": [
    {
      "index": 0,
      "uuid": "GPU-aaaa-1111",
      "name": "NVIDIA A100-SXM4-80GB",
      "gpu_utilization_percent": 85,
      "memory_used_mib": 57344,
      "memory_total_mib": 81920
    },
    {
      "index": 1,
      "uuid": "GPU-bbbb-2222",
      "name": "NVIDIA A100-SXM4-80GB",
      "gpu_utilization_percent": 20,
      "memory_used_mib": 12288,
      "memory_total_mib": 81920
    }
  ]
}

get_gpu_metrics (with {"index": 0} or {"uuid": "GPU-aaaa-1111"}):

json

{
  "index": 0,
  "uuid": "GPU-aaaa-1111",
  "name": "NVIDIA A100-SXM4-80GB",
  "gpu_utilization_percent": 85,
  "memory_utilization_percent": 70,
  "memory_used_mib": 57344,
  "memory_total_mib": 81920,
  "temperature_celsius": 72,
  "power_draw_watts": 300,
  "power_limit_watts": 400,
  "pcie_tx_kbps": 0,
  "pcie_rx_kbps": 0,
  "nvlink_tx_mbps": 0,
  "nvlink_rx_mbps": 0
}

gpu_summary:

json

{
  "device_count": 2,
  "avg_gpu_utilization": 52.5,
  "avg_memory_utilization": 42.5,
  "total_memory_used_mib": 69632,
  "total_memory_total_mib": 163840,
  "max_temperature_celsius": 72,
  "total_power_draw_watts": 375
}

MIG instances add is_mig, parent_gpu, and mig_profile fields to the get_gpu_metrics and list_gpus payloads.

Quick start

bash

# build (requires CGO + NVML headers on Linux)
make build

# run the server communicates over stdio
./gpu-mcp-server

Claude Desktop

Add to claude_desktop_config.json:

json

{
  "mcpServers": {
    "gpu": {
      "command": "/path/to/gpu-mcp-server"
    }
  }
}

Goose

yaml

extensions:
  gpu-metrics:
    type: stdio
    cmd: /path/to/gpu-mcp-server

Cursor

Add to .cursor/mcp.json for a project, or ~/.cursor/mcp.json for all projects:

json

{
  "mcpServers": {
    "gpu": {
      "type": "stdio",
      "command": "/path/to/gpu-mcp-server"
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json

{
  "mcpServers": {
    "gpu": {
      "command": "/path/to/gpu-mcp-server"
    }
  }
}

Build

Requires Go 1.23+, CGO, and NVIDIA drivers on the target machine.

bash

make build       # compile binary
make test        # run tests (no GPU needed uses mock)
make lint        # golangci-lint
make docker      # container image

Tests use a mock collector, so they run anywhere no GPU hardware required.

Docker

Prebuilt multi-arch images (linux/amd64, linux/arm64) are published to GHCR on every release.

bash

docker pull ghcr.io/pmady/gpu-mcp-server:latest
docker run --rm -i --gpus all ghcr.io/pmady/gpu-mcp-server:latest

The host needs the NVIDIA Container Toolkit installed for --gpus all to work. The server speaks MCP over stdio, so the -i flag is required — don't drop it.

json

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

Pin a specific version via tag instead of :latest, e.g. ghcr.io/pmady/gpu-mcp-server:v0.1.0.

Architecture

code

Agent (Claude/Goose) ─── MCP (stdio) ──→ gpu-mcp-server ──→ NVML ──→ GPU
                                              │
                                         Tools:
                                         • list_gpus
                                         • get_gpu_metrics
                                         • gpu_summary

The server runs as a local process alongside the agent. It calls NVML directly through cgo — no sidecar, no network hops, no metric pipeline to configure.

Project info

License: Apache 2.0
Language: Go
AAIF project alignment: MCP
Related: keda-gpu-scaler (GPU autoscaling for Kubernetes)
Whitepaper: GPU-Aware Autoscaling in Cloud Native AI Infrastructure — CNCF TAG Infrastructure initiative (TOC #2188)

Citing

If you use gpu-mcp-server in your research or writing, please cite it via its DOI. Full citation metadata is in CITATION.cff.

bibtex

@software{madduri_gpu_mcp_server,
  author    = {Madduri, Pavan},
  title     = {gpu-mcp-server: NVIDIA GPU metrics for AI agents over the Model Context Protocol},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.22866670},
  url       = {https://doi.org/10.5281/zenodo.22866670}
}

Roadmap

See ROADMAP.md for the 12-month public roadmap.

Contributing

See CONTRIBUTING.md for how to get involved.

Contributors

Thanks to all our contributors! Add yourself via PR.

Governance

This project follows Linux Foundation Minimum Viable Governance.

Documentation

Full documentation - hosted on Read the Docs
ROADMAP.md - public roadmap
GOVERNANCE.md - decision-making process
DEPENDENCIES.md - external dependencies and licenses
SECURITY.md - vulnerability reporting
AGENTS.md - instructions for AI agents working on this repo
CODE_OF_CONDUCT.md - community standards

GPU MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

Topics

gpu-mcp-server

Tools

Sample output

Quick start

Claude Desktop

Goose

Cursor

Windsurf

Build

Docker

Architecture

Project info

Citing

Roadmap

Contributing

Contributors

Governance

Documentation

Star History

Install

Related servers