Turn YouTube into a research source for AI. MCP server for searching, transcripts, comments, and multi-video analysis.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"youtube-research-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# YouTube Research MCP [](https://github.com/lee-s-dev/youtube-research-mcp/actions/workflows/tests.yml)  [🇰🇷 한국어](README.md) > "The real insight in a YouTube video lives in the **comments**." An MCP server that turns YouTube into a **multi-dimensional research source** for your AI assistant. Cross-reference what creators say (transcripts) with what viewers actually think (comments), and run complex multi-video research — all handled directly by your AI. **Core features work without an API key.** Comment analysis requires a YouTube Data API key. --- ## What can you do with this? - **Compare multiple videos** — Collect transcripts from several videos on the same topic and find common claims, contradictions, and patterns - **Analyze audience sentiment** ⚠️ API key required — Pull comments alongside transcripts to compare "what creators say" vs "what viewers actually think" - **Track channel trends** — Analyze a channel's recent videos to see what topics they're focusing on - **Summarize any video** — Give your AI a URL and get the key points extracted immediately > YouTube as a *reading* research source, not a *watching* platform. ### ✨ See what's possible **👤 You type (with API key):** > "Summarize the pros and cons from this review video, and tell me the top 3 complaints that keep coming up in the comments." **🤖 AI responds:** > "The creator highlighted camera performance and battery life as key strengths. However, **analyzing the collected comments**, the most frequently mentioned complaints from actual users were: ① overheating issues, ② frame drops in certain apps, and ③ slow charging speed. There's a noticeable gap between the creator's positive take and real-world user experience." --- ## Feature Overview | Feature | Without API key | With API key | …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.