GPU Server
MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
Servidor MCP · de moezdil
Resumo
GPU Server é um servidor MCP publicado por moezdil. Marketplaces que lemos e que o listam: 1 (Official MCP Registry). Vimos pela primeira vez em 2026-10-21 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-11-04.
O que pede
- Roda na sua máquina
Nenhum dos marketplaces que lemos publica as ferramentas ou as configurações que ele pede.
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Pacote
PyPI gpu-server (gpu-server no PyPI)
- Downloads do PyPI por semana: 22 (2026-11-03)
- Downloads do PyPI por mês: 0 (2026-11-03)
- Última versão no PyPI: 0.2.2, publicada em 2026-10-21
Os dados do PyPI vêm do pypi.org e os downloads do PyPI do pypistats.org. Cada número é do próprio registro e nunca é somado a outro. Um registro que não publica um número não mostra nenhum: sem número não é zero.
Funciona com
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Um link de um clique abre o cliente, que pede confirmação antes de adicionar o servidor.
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como servidor MCP local: pacote PyPI
Gerado a partir do que Official MCP Registry declara.
claude mcp add --transport stdio mcp-gpu-server -- uvx gpu-server[mcp_servers.mcp-gpu-server]
command = "uvx"
args = ["gpu-server"]{
"mcpServers": {
"mcp-gpu-server": {
"command": "uvx",
"args": [
"gpu-server"
]
}
}
}Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir o registro) | Listado | 0.2.2 | Downloads por mês (PyPI): 0 Downloads por semana (PyPI): 22 Forks (GitHub): 1 Estrelas (GitHub): 0 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
O que mudou
- Passou a ser um produto que acompanhamos
- Official MCP Registry: apareceu
Forks e cópias
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta lista.
-
MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
-
Read-only NVIDIA GPU monitor: bottlenecks, VRAM forecast, crash diagnosis, pre-render check, jobs.
-
NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.
-
hardware-probe io.github.yamaru-eu/hardware-probe
Hardware probe for performance diagnostics, thermal monitoring, and LLM optimization.
-
Run GPU acceptance tests on your NVIDIA GPU nodes over SSH: DCGM, GEMM, HBM/PCIe bandwidth, NCCL.
-
Fetch and analyze BP5 data files using ADIOS2. Access scientific data, metadata, and attributes...
-
Linux MCP server for real-time system monitoring - CPU, memory, disk, network, processes, Docker.
-
GPU cloud platform — create, manage, and monitor instances, snapshots, SSH keys, and billing.
-
Query system performance metrics via MCP - CPU, memory, disk I/O, network, processes
-
Rent a per-minute GPU from your MCP client, run a job, download results, shut it down.
Plugins semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em Claude Code: claude-plugins-community (5)
-
Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more.
-
MCP server for terminal commands, file operations, and process management
-
nodebench io.github.HomenShum/nodebench
260 MCP tools across 49 domains. AI Flywheel, quality gates, research, web scraping.
-
Cloud cost + FinOps knowledge for AI agents: AWS/Azure/GCP optimisation, AI spend, waste playbooks.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
Listado em Claude Code: claude-plugins-official (5)
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
-
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom…
-
MCP server for terminal commands, file operations, and process management
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
Listado em Claude: knowledge-work-plugins (5)
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
MCP server for terminal commands, file operations, and process management
-
Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts
-
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
Listado em Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Comprehensive skill for the entire Temporal lifecycle — developing applications, using the Temporal CLI, running and managing Temporal Server, and working with Temporal Cloud.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
Listado em Community GitHub marketplaces (5)
-
Node Hardware MCP - Comprehensive Hardware Monitoring and System Analysis for LLMs with real-time performance metrics
-
Run a GPU job under a hard dollar cap and collect the files it writes.
-
Every NinjaOne report, plus a local store that answers fleet-wide questions no single API call can
-
Every Better Stack Uptime feature, plus an offline SQLite mirror and cross-resource fleet analytics
-
Fleet-wide backup triage, stale-backup detection, and cross-engine analytics for any MCP agent.
Listado em Copilot CLI: github/awesome-copilot (5)
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Explore and query TimeBase streams, schemas, QQL, symbols, and server status via MCP.
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
See a live map of the Copilot agents on your computer, their sub-agents, their commands, and where their data goes.
-
Use Datadog directly in Copilot / VS Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation.
Listado em Copilot CLI: github/copilot-plugins (5)
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Analyze MSVC build performance using vcperf.exe and ETL traces.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
Listado em Cursor: cursor/plugins (5)
-
Let Grok Bot reach MCP servers on your private Tailscale network: connect your own tailnet, or your team's company tailnets turned on by a team admin, with each member using their…
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Inspect and manage feature gates, experiments, dynamic configs, and metrics.
-
Work with PostHog from chat: query product analytics and run SQL, manage feature flags and experiments, triage error tracking issues, and review session replays, surveys, and…
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
Listado em Docker MCP Catalog (5)
-
MCP server for Polar Signals Cloud continuous profiling platform, enabling AI assistants to analyze CPU performance, memory usage, and identify optimization opportunities in…
-
MCP server providing Prometheus metrics access and PromQL query execution for AI assistants
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
VeyraX MCP is the only connection you need to access all your tools in any MCP-compatible environment.
-
Dynatrace-mcp io.github.dynatrace-oss/Dynatrace-mcp
[DEPRECATED] Dynatrace MCP Server. Migrate to dynatrace-for-ai or Dynatrace Remote MCP Server.
Listado em Official MCP Registry (5)
-
MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
-
Read-only NVIDIA GPU monitor: bottlenecks, VRAM forecast, crash diagnosis, pre-render check, jobs.
-
NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.
-
hardware-probe io.github.yamaru-eu/hardware-probe
Hardware probe for performance diagnostics, thermal monitoring, and LLM optimization.
-
Run GPU acceptance tests on your NVIDIA GPU nodes over SSH: DCGM, GEMM, HBM/PCIe bandwidth, NCCL.
Listado em PyPI (MCP servers) (5)
-
runpod com.mcparmory/runpod
Launch, scale, and manage GPU pods and serverless endpoints across regions
-
sentry com.mcparmory/sentry
Track errors, manage performance alerts, and configure dashboards and monitors
-
Proxmox VE MCP server for VMs, LXCs, snapshots, backups, storage, and cluster operations.
-
datadog com.mcparmory/datadog
Monitor infrastructure, manage agents and deployments, track metrics, logs, and events
-
MCP server for Zabbix monitoring and automation
Listado em npm registry (MCP servers) (5)
-
MCP server for interacting with Runpod API
-
Expanded Model Context Protocol (MCP) server for Call Telemetry lab, fleet, and appliance management across Proxmox VE (ESXi is retired).
-
SutramX uptime monitoring: monitors, check results, incidents, status pages and uptime/SLO reports.
-
mcp dev.aicommander/mcp
Remote shell and detached long-running jobs on your own machines — no SSH, open ports or VPN.
-
Hanzo MCP Server - Unified tool surface with AI, cloud control, vector search, and multi-framework UI
Encontrados pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Quer esta marca no seu plugin em nosso catálogo?
Prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS, e você poderá mostrar esta marca na ficha, com banners ao vivo para o seu site e o README. Como funciona a verificação
Você também recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Official MCP Registry. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.