GPU Server
MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
Servidor MCP · de moezdil
Resumen
GPU Server es un servidor MCP publicado por moezdil. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). Lo vimos por primera vez el 2026-10-21 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-11-04.
Qué pide
- Se ejecuta en tu equipo
Ninguno de los marketplaces que leemos publica sus herramientas ni los ajustes que pide.
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Paquete
PyPI gpu-server (gpu-server en PyPI)
- Descargas de PyPI por semana: 22 (2026-11-03)
- Descargas de PyPI por mes: 0 (2026-11-03)
- Última versión en PyPI: 0.2.2, publicada el 2026-10-21
Los datos de PyPI proceden de pypi.org y las descargas de PyPI de pypistats.org. Cada cifra es del propio registro y nunca se suma a otra. Un registro que no publica una cifra no muestra ninguna: sin cifra no es cero.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Un enlace de un clic abre el cliente, que pide confirmación antes de añadir el servidor.
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como servidor MCP local: paquete PyPI
Generado a partir de lo que declara Official MCP Registry.
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"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.2.2 | Descargas por mes (PyPI): 0 Descargas por semana (PyPI): 22 Forks (GitHub): 1 Estrellas (GitHub): 0 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Qué cambió
- Pasó a ser un producto que seguimos
- Official MCP Registry: apareció
Forks y copias
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta 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 similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en 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…
Publicado en 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…
Publicado en 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…
Publicado en 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…
Publicado en 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.
Publicado en 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.
Publicado en 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.
Publicado en 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.
Publicado en 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.
Publicado en 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.
Publicado en 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
Publicado en 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 por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Official MCP Registry. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.