What it does
The server turns three kinds of source into Markdown. YouTube captions are split into chunks that keep their timestamps, PDFs keep their page numbers, and web pages are converted to clean Markdown, as the publisher describes.
The name points to retrieval-augmented generation (RAG) ingestion, so it may suit preparing video transcripts, PDF documents or web content as text for a retrieval workflow. The source gives no details on setup or how to run it.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Kizuki RAG Ingest
YouTube captions (chunks, timestamps), PDFs (page numbers) and web pages as clean Markdown.
v1.0.1As shown on registry.modelcontextprotocol.io when we last read it