What it does
The server returns YouTube transcript text with timestamps, taken from the caption tracks already available for a video. It is listed under development and is published by rocosen.
It suits workflows that need the spoken text of a YouTube video with its timing, for example when an AI tool should read or search a transcript.
It is built around the FlashData API, which is a paid service, so using the server means access to that API.
Limitations and requirements
Requires access to the paid FlashData API. Transcripts come only from existing caption tracks.
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 18 Nov 2026 · its page on the source
YouTube Transcript — FlashData
YouTube transcript text with timestamps from existing caption tracks. Paid FlashData API.
v0.1.2As shown on registry.modelcontextprotocol.io when we last read it