NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "video-search-and-sum": {
      "command": "npx",
      "args": [
        "-y",
        "NVIDIA-AI-Blueprints/video-search-and-summarization"
      ]
    }
  }
}

README Excerpt

<h2>NVIDIA AI Blueprint: Video Search and Summarization (VSS)</h2> - [Overview](#overview) - [Use Case / Problem Description](#use-case--problem-description) - [Agent Workflows](#agent-workflows) - [Software Components](#software-components) - [Target Audience](#target-audience) - [Repository Structure Overview](#repository-structure-overview)

Topics

computer-visiongenerative-ailong-video-understandingmodel-context-protocolmultimodal-ainatural-language-searchnvidia-nimragreal-time-video-analyticsretrieval-augmented-generationskillsvideo-agentvideo-analyticsvideo-ragvideo-search

video-search-and-summarization

Quick Install

README Excerpt

Topics

Related AI/LLM Servers