"NVIDIA" matching MCP servers:

Enables LLM agents to control NVIDIA Run:AI infrastructure by dynamically searching and executing over 426 Run:AI APIs through MCP tools.

Deterministic AI data-center design tools for sizing, validation, and conceptual rack/site layouts. Supports NVIDIA Hopper, Blackwell, and Rubin profiles. Calculations require a registered AIDC API key; results preserve warnings, RFIs, and pending validations.

Provides GPU-accelerated gradient boosting model training and inference through a cloud service. Enables AI agents to train models on NVIDIA A10G GPUs and get fast cached predictions with portable model artifacts.

Exposes NVIDIA Run:ai documentation and API references across multiple versions and docsets (self-hosted, SaaS, multi-tenant, API, legacy) through MCP tools.

VibOps MCP is the control plane between your AI agents and your GPU infrastructure. 74 tools covering: GPU fleet management (deploy, scale, monitor across NVIDIA, AMD, Intel, AWS, Google, Groq), Agent Infrastructure Control Plane (per-agent GPU cost, budget enforcement, model policies, dependency graph), governance (AI Act, SOC 2, immutable HMAC audit chain), and GPU FinOps (chargeback, waste..)..