YouTube Intelligence
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve YouTube Intelligence from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.