A simple MCP server by Michael Hanson that enables AI assistants to fetch and analyze YouTube video transcripts by providing a single get-transcript tool that accepts YouTube URLs or video IDs. The implementation extracts transcript data and formats it with timestamps in [XmYs] format, making it easy for LLMs to summarize videos, identify key points, or analyze arguments without needing to watch the content directly. Built with Bun and TypeScript, it can be easily installed via bunx or npx and integrates seamlessly into any MCP-compatible AI application for video content analysis workflows.
Cognium trust score
97%
Tier
Verified
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 2026-09-28.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.