MCP servers
122,089 servers from the official registry, GitHub and npm. Filter by category, transport and language.
122,089 servers from the official registry, GitHub and npm. Filter by category, transport and language.
Lets an AI assistant inspect Kodi, diagnose playback problems, and apply reversible configuration changes to NVIDIA Shield and Android TV devices.
MCP server that gives Claude, Cursor and any AI agent free access to 100+ NVIDIA-hosted models (Nemotron, Llama, GPT-OSS, DeepSeek, vision, embeddings) with automatic task routing and parallel multi-model fan-out.
Enables AI assistants to access the NVIDIA Elements design system, component APIs, design tokens, and UI templates for AI/ML and robotics development.
$claude mcp add elements-26bdc8 -- npx -y @nvidia-elements/cliLets AI assistants look up UI component APIs, design tokens, examples, imports, and validation for building NVIDIA-style web interfaces.
$claude mcp add elements -- npx -y @nvidia-elements/cliControls NVIDIA Isaac Sim via MCP to create robots, build scenes, run simulations, and debug physics from an AI client.
$claude mcp add isaacsim-mcp-server -- uvx isaacsim-mcp-serverGenerates and edits background music and sound effects locally using Stable Audio 3 on Apple Silicon or NVIDIA GPUs.
$claude mcp add audio-studio-mcp -- uvx audio-studio-mcpProvides a semantic layer for AI assistants to query databases with validated SQL and maintain a personal knowledge base with linked concepts.
Exposes real-time NVIDIA GPU metrics like utilization, memory, temperature, and power to AI agents via the Model Context Protocol.
$claude mcp add gpu-mcp-server -- docker run -i --rm ghcr.io/pmady/gpu-mcp-server:v0.1.0Rent NVIDIA GPU pods, run commands, and manage multi-node clusters via a Python SDK and CLI with per-second billing.
$claude mcp add lium -- uvx lium.ioAllows AI agents to browse, lease, and run workloads on real NVIDIA GPUs with onchain payments and confidential computing capabilities.
$claude mcp add mcp -- npx -y @prismnetwork/mcpAllows an AI agent to compare GPU compute costs, rent instances, run training jobs, and manage files via an OpenAI-compatible API and secure orchestration.
$claude mcp add cloudgpu-mcp -- npx -y cloudgpu-mcpLets an AI agent drive a live Isaac Sim session to tune robot gains, perform range tests, and manage Isaac Lab training runs.
$claude mcp add dex-isaac-mcp -- uvx dex-isaac-mcpAllows an AI agent to rent per-minute GPUs, run compute jobs, manage files, and access an OpenAI-compatible model API.
$claude mcp add cloudgpu-mcp -- npx -y cloudgpu-mcpAllows an AI client to provision GPU compute capacity using account-based billing or x402 USDC payments.
$claude mcp add kilawatt-mcp-server -- npx -y kilawatt-mcp-serverLets an AI client monitor NVSentinel state and inject faults into simulated GPUs on a Kubernetes lab cluster.
$claude mcp add nvidia-nvsentinel-mcp -- docker run -i --rm docker.io/omerfsen/nvidia-nvsentinel-mcp:0.5.1Monitors the health of local AI stacks by checking Ollama nodes, NVIDIA GPUs, and tailnet peers with graded confidence findings.
$claude mcp add stack-guardian -- uvx stack-guardianAllows AI agents to compile, run, and debug CUDA and HIP kernels on a CPU to detect memory errors, race conditions, and synchronization bugs.
$claude mcp add cuda4cpu -- docker run -i --rm ghcr.io/javier-cabezas/cuda4cpu:0.6.0Transcribes audio and video files into subtitles and text using local GPU acceleration across AMD, NVIDIA, Intel, and Apple hardware.
$claude mcp add babelscribe -- uvx babelscribeProvides an MCP control plane to execute ComfyUI workflows with explicit approvals, cryptographic model identity, and durable run evidence.
$claude mcp add local-gpu-imagegen -- uvx local-gpu-imagegenDetermines if open-weight LLMs fit on specific GPUs and provides hardware recommendations and VRAM estimates.
$claude mcp add vram-mcp -- npx -y @nodegrove/vram-mcp