"NVIDIA" matching MCP servers:

Enables AI agents to consume 50+ NVIDIA NIM models including LLMs, image generation, and vision through 10 MCP tools with rich metadata and advanced filtering.

Enables AI agents to access 140+ NVIDIA NIM models for chat, embeddings, reranking, vision, image generation, OCR, and content safety via stdio.

Enables users to get expert help with Isaac Sim scripting, USD (Universal Scene Description), Python snippets, and API usage through NVIDIA's USDCode AI assistant. Provides specialized guidance for 3D graphics and simulation development workflows.

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

MCP server for reading, filtering, and analyzing NVIDIA Nsight Graphics captures via ngfx-replay, exposing tools for capture inspection, GPU Trace profiling, and replay analysis.

Enables AI agents to access the Nvidia Supplier Map 2026 dataset, querying supplier edges by tier, supplier, ticker, or honesty flag. The free tier provides structural data, while a token-gated paid tier adds verbatim evidence quotes, source URLs, and filing dates.

CP server that generates AGENTS.md and CLAUDE.md from your real repo, verifies every command actually exists, detects doc drift, and saves session context — all locally, no data leaves your machine. Free-tier friendly via Groq/NVIDIA.

A flight recorder and memory server that sits between MCP clients and Blender, recording interactions, distilling them into persistent per-file memory using NVIDIA Nemotron, and serving that memory to agents via MCP tools like recall and search_sessions.

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