Skip to main content
Glama
521,294 tools. Updated 2026-09-06 10:44

"NVIDIA" matching MCP tools:

  • Routes NVIDIA AI questions to the optimal model and reasoning approach by evaluating dependency depth in a knowledge graph.
    MIT
  • Find NVIDIA AI concepts by keyword and domain to identify dependencies and prerequisites for development tasks.
    MIT
  • Traverse the NVIDIA AI knowledge graph to discover dependencies and dependents of a given concept within a specified domain.
    MIT
  • Monitor NVIDIA GPU performance by reading live nvidia-smi telemetry data.
    MIT

Matching MCP Servers

Matching MCP Connectors

  • NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.

  • NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.

  • Loads .ply or .splat Gaussian Splat assets into TouchDesigner, sets up a renderTOP output, and optionally attaches an existing camera for interactive viewing.
    MIT
  • Look up the ticker for a US stock or ETF from a company name, fund name, or partial ticker. Use it when you need to confirm the exact ticker before running other PairBook tools.
    MIT
  • Convert any 2D image or video into a depth map for TouchDesigner using Depth Anything v2, eliminating the need for Kinect or RealSense hardware.
    MIT
  • Get a second opinion from another AI model or route a task to a specialized model. Choose coding, reasoning, budget, or free modes, or specify a custom model for the job.
    MIT
  • Bridge TouchDesigner with external systems: OSC/MIDI control, DMX/Art-Net lighting output, RTMP streaming, and NDI/Syphon video input/output.
    MIT
  • Search for companies, people, and patents in the financial knowledge graph by name, ticker, or keyword. Filter results by type, sector, or limit.
    MIT
  • Create an Omniverse/USD stage sync scaffold with Nucleus metadata, layer maps, variant maps, and live-session notes for real-time collaboration.
    MIT
  • Run a single prompt across multiple AI models simultaneously to compare responses and verify accuracy through consensus.
    MIT
  • Offload large, mechanical, or exploratory coding work to a sandboxed sub-agent that reads the repository and returns a written report, saving your context.
    MIT
  • Need to know if a remote machine is up? This check verifies online status, reachability, readiness, screen-sharing availability, and NVIDIA GPU usage before connecting.
    MIT
  • Fact-check any claim by returning a verdict (supported, contradicted, partially supported, or unverifiable) with confidence score, evidence chain from verified sources, and source reliability ratings.
    MIT