MCP SERVERPull a YouTube video's official captions with per-segment timestamps, fall back to Whisper ASR when there are none, and keep the results in a searchable library.
LABSCO SUMMARY
fetch_transcript is free and fails with NO_CAPTIONS, and that specific error is where transcribe_video is documented as the next move; the transcription costs 5 credits and debits only on success, while polling its progress with get_asr_task costs nothing at all. The recommended polling interval is stated as 3-5 seconds, so an agent does not have to guess at it. Discovery is split by situation rather than by object — topic search when no channel is known, in-channel search when one is, the paginated listing for a back catalogue and the shortcut for recent uploads — which usually settles the choice of tool before you make it.
A YouTube research client: search and channel discovery, video metadata, official transcripts, an asynchronous Whisper transcription path for videos without captions, and a saved library.
An authenticated user for the library, since save_to_library, list_library and get_library_item are scoped to the calling user's own data. Credits for AI transcription: transcribe_video costs 5 credits, debited only on successful completion, while the metadata, caption and library reads are free.
Add the hosted endpoint, then sign in — paste it into your client, then approve the OAuth sign-in
USE CASES
Metadata reports whether captions exist before you spend a call finding out, and the transcript comes back with per-segment timestamps and the language it detected. Both are free.
The ASR job runs in the background and returns a task id immediately, with a progress state to poll every few seconds. The 5 credits are debited only if it finishes, and the result can be filed straight into the library.
A handle or a URL resolves to a canonical channel id first, because the channel-scoped tools need it. From there the search is restricted to that channel rather than the whole of YouTube.
Channel listings are newest first with a continuation token when there is more, and playlist listings keep each video's position, so a series can be followed in the order it was meant to be watched.
The library holds transcripts and summaries scoped to your own account, searchable by title or author with a favourites filter, and one item returns its full content inline.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
fetch_transcriptFetch the existing official transcript (subtitles/captions) of a YouTube video, with per-segment timestamps and language detected. Errors with NO_CAPTIONS if the video has no captions — fall back to transcribe_video in that case to generate one with AI ASR. This call is free.
fetch_video_infoFetch consolidated YouTube video metadata with numeric types — title, channel, duration, view count, publish date, thumbnail, description, captions availability. Does NOT include the transcript itself; call fetch_transcript or transcribe_video for that. Cheap, fast, free.
get_asr_taskPoll the status of an ASR task created by transcribe_video. Returns one of queued, downloading, transcribing, finalizing, done, or failed. When status is done, includes the full transcript with timestamps. Recommended polling interval: 3-5 seconds. Free — does not consume credits.
get_channel_latest_videosGet the most recent videos from a YouTube channel — convenience wrapper over list_channel_videos with no pagination. Best for 'what did this creator publish recently?' style queries.
get_library_itemRead a saved Library item with its transcript and AI summary inline (when available). Use after list_library to fetch the full content the user saved. Free.
list_channel_videosList all videos from a YouTube channel ordered by publish date (newest first), with pagination. Returns up to 30 per page plus a continuation token if more results exist. For just the most recent handful, prefer get_channel_latest_videos for simplicity.
list_libraryList videos the user has saved to their Library (transcripts + summaries). Supports substring search on title/author, favorites filter, and pagination. Returns recently saved items first. Scoped to the calling user's data only.
list_playlist_videosList videos in a YouTube playlist in order, with pagination. Returns video metadata and position within the playlist. Works for any public or unlisted playlist exposed by its URL/ID.
resolve_channelResolve a YouTube @handle, channel URL, video URL, or raw channel ID into canonical channel info (channel ID, name, handle, subscriber count, video count, avatar). Call this first when you only have a handle or URL but need a channel ID for the other channel-scoped tools.
save_to_librarySave a video to the authenticated user's Library. Three modes via kind: 'asr' bookmarks the video and flips has_asr (use after a successful transcribe_video → fetch_transcript flow); 'summary' uploads a summary blob; 'both' does both at once. Idempotent: saving the same video twice updates the existing entry.
search_channel_videosSearch for specific videos within a single YouTube channel. Restricts results to the given channel. Use after resolve_channel if starting from a handle. Useful for 'find Karpathy's video about backpropagation' style queries.
search_youtubeSearch YouTube globally for videos, channels, or playlists on any topic. Returns up to 50 results with metadata. Use this for topic-based discovery when the user has not specified a channel — for searching within a known channel use search_channel_videos instead.
transcribe_videoStart an asynchronous AI ASR (Whisper) transcription of a YouTube video. Returns immediately with a task_id and estimated_wait_seconds; the actual transcription runs in the background. Poll status with get_asr_task. Use this when fetch_transcript returned NO_CAPTIONS or when the video has no captions. Costs 5 credits, debited only on successful completion.
BEFORE YOU INSTALL
13 tools when we connected. save_to_library is the only write. transcribe_video starts a job; collect the result with get_asr_task.
A client that can reach a remote MCP server over HTTP
Both documented setups connect to a hosted endpoint.
CONTEXT COST
Rated by the size of the 13 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
https://api.subdownload.com/mcpAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
{
"mcpServers": {
"subdownload": {
"url": "https://api.subdownload.com/mcp"
}
}
}{
"mcpServers": {
"subdownload": {
"url": "https://api.subdownload.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}MCP servers
sinjab
MalikElate
ZeroPointRepo
kimtaeyoon83