YouTube Intelligence
Extracts YouTube video metadata, transcripts, and comments via yt-dlp with server-side LLM summarization, entity extr...
What it does
Extracts YouTube video metadata, transcripts, and comments via yt-dlp with server-side LLM summarization, entity extraction, topic segmentation, and channel monitoring for content research workflows.
Integrates with YouTube through yt-dlp to extract video metadata, transcripts, comments, and channel feeds. Performs server-side processing to reduce token usage, compressing transcripts from thousands of tokens down to 200-500 tokens before passing them to LLM context windows. Supports multiple LLM providers including OpenAI, Anthropic, Google, Ollama, vLLM, and LM Studio, with automatic fallback to extractive summarization when no API keys are configured. Provides nine tools covering video analysis reports, transcript extraction, comment sentiment analysis, entity extraction, topic segmentation, YouTube search, playlist processing, channel monitoring via RSS, and stored transcript search with SQLite or PostgreSQL caching.
Capabilities
Server
Quality
deterministic score 0.64 from registry signals: · indexed on pulsemcp · has source repo · 45 github stars · registry-generated description present