Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
GPU Server
MCP serversMCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
mcp-gpu-server@0.1.3 -
GPU Server
MCP serversMCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
gpu-server@0.2.2 -
SkillSpector
SkillsSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
git clone https://github.com/NVIDIA/SkillSpector.git -
cuvs
AI repositoriescuVS - a library for vector search and clustering on the GPU
git clone https://github.com/NVIDIA/cuvs.git -
isaacsim-mcp-server
MCP serversControl NVIDIA Isaac Sim robotics simulator through MCP with 42 tools
isaacsim-mcp-server@0.6.1 -
GPU MCP Server
MCP serversNVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.
ghcr.io/pmady/gpu-mcp-server:v0.1.0 -
mcp
MCP serversRent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain.
@prismnetwork/mcp@0.8.4 -
ckg-nemotron-perplexity
MCP serversNVIDIA Nemotron + Perplexity Sonar as knowledge graphs — 2 domains, 83 nodes. MCP-native.
ckg-nemotron-perplexity@0.2.1 -
Omniverse MCP
MCP serversLet an AI assistant work in NVIDIA Isaac Sim and other Omniverse Kit apps
omniverse-mcp@0.5.1 -
mcp
MCP serversRent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain.
@prismnetwork/mcp@0.10.0 -
Tachyon GPU monitor
MCP serversRead-only NVIDIA GPU monitor: bottlenecks, VRAM forecast, crash diagnosis, pre-render check, jobs.
https://github.com/formray/tachyon/releases/download/v1.2.0/tachyon-1.2.0-windows-x64.mcpb@1.2.0 -
Kodecz
MCP serversRender, preview and check videos written as web pages (HTML to MP4 on NVIDIA GPU or CPU)
kodecz-mcp@0.1.0 -
project-maya
AI repositoriesProject Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
git clone https://github.com/mw00/project-maya.git -
Automodel
AI repositories🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
git clone https://github.com/NVIDIA-NeMo/Automodel.git -
AI Video Enhancer Studio
MCP serversUpscale, stabilize, denoise and raise the frame rate of videos locally on your NVIDIA GPU
@contentasoft/ai-video-enhancer-mcp@1.0.2 -
NIM Key Manager
MCP serversSelf-hosted NVIDIA NIM API-key manager with a Claude MCP connector; deploy your own instance.
-
babelscribe
MCP serversOffline speech-to-text and SRT subtitles in 99 languages on your own AMD/NVIDIA/Intel/Apple GPU.
babelscribe@0.4.0 -
self-hosted-ai
MCP serversEngineering log of self-hosted AI on NVIDIA DGX Spark (GB10/SM121A). 60+ articles indexed.
-
NVSentinel Lab
MCP serversTest NVIDIA NVSentinel on a kind lab: read its state and inject faults into a simulated GPU.
docker.io/omerfsen/nvidia-nvsentinel-mcp:0.5.1 -
TensorRT-Model-Connect
Agents & frameworksFrom PyTorch model to end-to-end TensorRT inference experience in two commands—AI-native, cross-platform, and built for the best possible user experience.
git clone https://github.com/NVIDIA/TensorRT-Model-Connect.git -
VMware Private AI (GPU & Model Serving)
MCP serversVMware Private AI (NVIDIA): GPU inventory, vGPU profiles, utilization, model serving — 20 tools
vmware-privateai@2.5.3 -
Lium GPU Cloud
MCP serversRent NVIDIA GPU pods on Lium, run commands on them and remove them, billed per second.
lium.io@0.45.1 -
Curator
AI repositoriesScalable data pre processing and curation toolkit for LLMs
git clone https://github.com/NVIDIA-NeMo/Curator.git -
ARADIA | sovereign & private agentic systems
MCP serversOn-prem Agentic AI on NVIDIA DGX. Query specs, model CapEx ROI, Purchase & join Partner Program.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.