AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
LLM Infra/
gpu-mcp-server
gpu-mcp-server logo

gpu-mcp-server

Active·★ 15·Apache-2.0·Updated 2026-10-17

gpu-mcp-server is an MCP-compatible server that exposes real-time NVIDIA GPU metrics as tools for AI agents. It allows agents like Claude, Goose, and Cursor to query utilization, memory, temperature, and power data without external monitoring systems.

#GPU Metrics#NVIDIA NVML#MCP Protocol#AI Agent Tools#Go Language#Real-time Monitoring#Containerization
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
$ Install
$ git clone https://github.com/pmady/gpu-mcp-server.git && cd gpu-mcp-server && make build
↗ Visit site★ GitHub
01

Features

01Exposes real-time NVIDIA GPU metrics as AI agent tools.
02Provides detailed GPU metrics including utilization, memory, temperature, and power.
03Supports Multi-Instance GPU (MIG) configurations.
04Offers PID-level GPU process attribution.
05Directly integrates with NVML, removing the need for external monitoring systems like Prometheus or dcgm-exporter.
02

Compatibility

Go
Language
Verified via docs
NVIDIA GPUs
Hardware
Verified via docs
Linux
OS
Verified via docs
Docker
Container
Verified via docs
Model Context Protocol (MCP)
Protocol
Verified via docs
03

Quick start

1
$ git clone https://github.com/pmady/gpu-mcp-server.git
2
$ cd gpu-mcp-server
3
$ make build
04

Use cases

↳Empowering AI agents with real-time NVIDIA GPU status and performance data.
↳Enabling AI models to make informed decisions based on GPU resource availability.
↳Integrating GPU monitoring capabilities directly into AI development environments (e.g., Cursor IDE).
↳Facilitating dynamic GPU resource management for AI workloads by providing instant metrics.
05

Alternatives

⚡Top VS:
VScloister★13→VSharnessrouter★3.2k→VSWRAI.TH★32→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
agentenv-framework
★357
→
cloister logo
cloister★ 13
Workerd-based hypervisor with a declarative Cap'n Proto manifest. Substrate-level identity, audit, and per-bundle credential scoping. Today's primary application: hosting MCP servers behind one HTTP face.
VSCompare→
harnessrouter logo
harnessrouter★ 3.2k
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
VSCompare→
WRAI.TH logo
WRAI.TH★ 32
Multi-agent orchestration via MCP. Persistent memory, inter-agent messaging, goal cascade, context budget pruning. One binary, zero config.
VSCompare→
agentenv-framework logo
agentenv-framework★ 357
Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.
VSCompare→
wigolo logo
wigolo★ 5.5k
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
VSCompare→
minibridge logo
minibridge★ 55
Make your MCP servers secure and production ready
VSCompare→
tunnel-client logo
tunnel-client★ 589
Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.
VSCompare→
emisar logo
emisar★ 331
An MCP that lets AI tools securely connect to your infrastructure, write IaaS code, debug issues, and assist during incidents - without risking production stability. Built for security teams to approve and infrastructure teams to experience like magic.
VSCompare→
See all alternatives →
pmady /
gpu-mcp-server
↗

MCP server for NVIDIA GPU metrics give AI agents real-time access to GPU utilization, memory, temperature, and power

15Apache-2.0
Last commit6d ago
StatusActive
CategoryLLM Infra
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit