youtube-transcripts
Free YouTube transcripts for AI agents — no API key, no account, no configuration.
What it can do
- Get Transcript: Fetch the transcript of a single YouTube video by URL or 11-character video ID. Serves the permanent cache instantly when available and otherwise fetches from YouTube (uncached fetches
- List Videos: List the videos of a YouTube channel or playlist: date, video ID, and title for each. Use this to answer questions about a channel — pick the relevant videos by title, then call get_trans
- Get Bulk Download Link: For a YouTube channel or playlist URL, returns a prefilled scripthaul.com link where the user can download every transcript as a ZIP for free. Bulk jobs cannot run over this ke
What data it sees
Do you need an account
No: the server works without sign-in
Free YouTube transcripts for AI agents — no API key, no account, no configuration. Three tools: get_transcript fetches a single video's transcript in clean text, timestamped, SRT, VTT, Markdown, or JSON, with optional language selection and honest labeling when YouTube won't translate; list_videos enumerates a channel or playlist (ID, title, date) so an agent can pick relevant videos and returns a typed video array; get_bulk_download_link produces a free scripthaul.com link that downloads every transcript in a channel or playlist as a ZIP. Cached transcripts serve instantly and unlimited; uncached fetches share a small daily per-IP allowance. Public captions only. Backed by scripthaul.com's transcript cache and fetch infrastructure.
Server tool list (4)
Raw names from tools/list. Only developers need these.
| get_transcript | Fetch the transcript of a single YouTube video by URL or 11-character video ID. Serves the permanent cache instantly when available and otherwise fetches from YouTube (uncached fetches are limited per IP per day). Formats: clean text, timestamped, both, srt, vtt, md, json. Costs 0 credits. Example prompt: "Get the transcript of https://youtu.be/jNQXAC9IVRw." |
| list_videos | List the videos of a YouTube channel or playlist: date, video ID, and title for each. Use this to answer questions about a channel — pick the relevant videos by title, then call get_transcript for each one. Listings are cached for a few hours; a fresh enumeration counts against the same daily allowance as uncached fetches. Costs 0 credits. Example prompt: "List the videos in https://www.youtube.com/@TED." |
| get_bulk_download_link | For a YouTube channel or playlist URL, returns a prefilled scripthaul.com link where the user can download every transcript as a ZIP for free. Bulk jobs cannot run over this keyless MCP server; they need the website. Costs 0 credits. Example prompt: "Give me a download link for every transcript in https://www.youtube.com/@TED." |
| get_latest_videos | Read up to the newest 15 public RSS entries from exactly one channel or playlist, cached for ten minutes. Costs 0 credits and no cold-fetch allowance. Separate allowance: 30 requests per IP per day shared across channels and playlists, including cached reads; resets at midnight UTC. Use a UC channel ID, an already-resolved channel alias, or a public playlist ID/URL; an unknown handle must first be resolved on the keyed API. This is a recent window, not a complete inventory. Example prompt: "What did channel UCAuUUnT6oDeKwE6v1NGQxug upload recently?" |