MCP Server
YouTube Transcript & Search MCP Server
com.transcriptout/youtube-transcript-and-youtube-search
What this MCP does
Searches YouTube, retrieves video and channel information, and obtains individual or bulk video transcripts.
Capabilities
Tools
14
tools
cancel_transcripts_job
Cancel batch job
Cancel a batch job. Credits are refunded ONLY for videos not started yet — anything already fetched stays in the results and stays paid for. Free.
Destructive
Idempotent
Input schema
{'type': 'object', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'description': 'id returned by submit_transcripts_job'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'status': {'type': 'string'}}, 'additionalProperties': True}
get_credits
Credit balance
Check the remaining credit balance of the API key. Free. Use it when the user asks how many credits are left, or before submit_transcripts_job to confirm a large batch fits the balance (the batch charges 1 credit per video on submit).
Read only
Input schema
{'type': 'object', 'required': [], 'properties': {}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'credits': {'type': 'integer'}, 'metered': {'type': 'boolean'}, 'user_id': {'type': 'string'}}, 'additionalProperties': True}
get_transcript
Get transcript
Get the transcript (subtitles) of a YouTube video. Accepts a video id or any YouTube URL. Set video_metadata=true to get the title, channel and duration in the SAME call — do not call get_video_info first, that is a second billed call for data this one already returns. format=text returns plain readable text (default, cheapest to read); format=json returns timed segments with start/duration in seconds; srt/vtt return ready subtitle file bodies and srv3 the raw YouTube XML. Prefer text unless you need timestamps or a file. Costs 1 credit.
Read only
Open world
Input schema
{'type': 'object', 'required': ['video'], 'properties': {'kind': {'enum': ['manual', 'auto'], 'type': 'string', 'description': 'Track kind. Omit to prefer a manual track and fall back to auto'}, 'lang': {'type': 'string', 'description': "Language code of the track, e.g. 'en', 'de'. Default 'en'."}, 'video': {'type': 'string', 'description': 'YouTube video id or URL'}, 'format': {'enum': ['text', 'json', 'srt', 'vtt', 'srv3'], 'type': 'string', 'description': "'text' = plain text (default), 'json' = timed segments, 'srt'/'vtt' = subtitle file body, 'srv3' = raw YouTube XML (srv3 does not combine with segment)"}, 'segment': {'type': 'integer', 'maximum': 5000, 'minimum': 20, 'description': 'Max characters per segment. Raise it when chunking the transcript for embeddings or retrieval — 500-1500 gives chunks with enough context; lower it for subtitle-sized lines. Left out, an auto-generated track is cut into ~180-character segments and a manual one is returned exactly as its author broke it, so pass this whenever you need one size regardless of which track answers.'}, 'video_metadata': {'type': 'boolean', 'description': "Include the video's title, channel, duration and views alongside the transcript. Replaces a separate get_video_info call — same one credit either way."}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'kind': {'type': 'string'}, 'language': {'type': 'string'}, 'metadata': {'type': 'object'}, 'video_id': {'type': 'string'}, 'transcript': {'description': 'format=json: array of {text, start, duration} segments (seconds); text/srt/vtt/srv3: one string in that format'}, 'available_langs': {'type': 'array'}}, 'additionalProperties': True}
get_transcripts_job
Batch job progress
Check the progress of a batch job: status (queued/running/done/cancelled), how many videos are ready, failed and still pending. Free — polling a job you already paid for costs nothing. Read the transcripts themselves with get_transcripts_results.
Read only
Input schema
{'type': 'object', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'description': 'id returned by submit_transcripts_job'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'done': {'type': 'integer'}, 'count': {'type': 'integer'}, 'ready': {'type': 'integer'}, 'failed': {'type': 'integer'}, 'status': {'type': 'string'}, 'pending': {'type': 'integer'}}, 'additionalProperties': True}
get_transcripts_result
One batch result
Read ONE video's result out of a batch job by its video id, without paging through get_transcripts_results. 404 means the job does not exist or this video has not finished yet — check get_transcripts_job before concluding anything. Free.
Read only
Input schema
{'type': 'object', 'required': ['job_id', 'video_id'], 'properties': {'job_id': {'type': 'string', 'description': 'id returned by submit_transcripts_job'}, 'video_id': {'type': 'string', 'description': 'one of the video ids the job was submitted with'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'status': {'type': 'string'}, 'video_id': {'type': 'string'}, 'transcript': {'description': 'format=json: array of {text, start, duration} segments (seconds); text/srt/vtt/srv3: one string in that format'}}, 'additionalProperties': True}
get_transcripts_results
Batch job results
Read finished transcripts from a batch job, in the order submitted. Results appear as they are fetched, so this can be called before the job is done. Each entry is exactly what get_transcript returns for that video, plus its status. Page with next_page_token. Free.
Read only
Input schema
{'type': 'object', 'required': ['job_id'], 'properties': {'limit': {'type': 'integer', 'description': 'Entries per page, 1-500 (default 100)'}, 'job_id': {'type': 'string', 'description': 'id returned by submit_transcripts_job'}, 'next_page_token': {'type': 'string', 'description': 'Token from a previous result'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'count': {'type': 'integer'}, 'results': {'type': 'array'}, 'has_more': {'type': 'boolean'}, 'next_page_token': {'type': 'string'}}, 'additionalProperties': True}
get_video_info
Get video info
Get metadata for one YouTube video (title, channel, duration, views, thumbnails) plus the list of available transcript languages, WITHOUT downloading the subtitles. Use it only when the transcript itself is not wanted. If you are going to fetch the transcript anyway, call get_transcript with video_metadata=true instead — it returns both for one credit, where these are two separate calls and two credits.
Read only
Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'YouTube video id or URL'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'title': {'type': 'string'}, 'available_langs': {'type': 'array'}}, 'additionalProperties': True}
latest_channel_videos
Latest channel videos
Get the ~15 most recent videos of a channel from its RSS feed. Fastest and cheapest way to check what a channel published recently.
Read only
Open world
Input schema
{'type': 'object', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': '@handle, channel name, UC... channel id or channel URL'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'videos': {'type': 'array'}, 'channel': {'type': 'string'}}, 'additionalProperties': True}
list_channel_videos
List channel videos
List videos from a channel's Videos tab, newest first. Accepts an @handle, a UC... channel id or a channel URL. ids_only=true returns just video ids (up to 500 per page) — use it when you only need ids to fetch transcripts.
Read only
Open world
Input schema
{'type': 'object', 'required': [], 'properties': {'name': {'type': 'string', 'description': '@handle, channel name, UC... channel id or channel URL (required unless paginating)'}, 'limit': {'type': 'integer', 'description': 'Page size. Up to 100, or up to 500 with ids_only'}, 'ids_only': {'type': 'boolean', 'description': 'Return video_ids[] instead of full video objects'}, 'next_page_token': {'type': 'string', 'description': 'Token from a previous result'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'count': {'type': 'integer'}, 'videos': {'type': 'array'}, 'channel': {'type': 'string'}, 'has_more': {'type': 'boolean'}, 'video_ids': {'type': 'array'}, 'next_page_token': {'type': 'string'}}, 'additionalProperties': True}
list_playlist_videos
List playlist videos
List videos of a playlist in playlist order. Accepts a PL... playlist id or a URL with list=. ids_only=true returns just video ids (up to 500 per page).
Read only
Open world
Input schema
{'type': 'object', 'required': [], 'properties': {'id': {'type': 'string', 'description': 'PL... playlist id or URL (required unless paginating)'}, 'limit': {'type': 'integer', 'description': 'Page size. Up to 100, or up to 500 with ids_only'}, 'ids_only': {'type': 'boolean', 'description': 'Return video_ids[] instead of full video objects'}, 'next_page_token': {'type': 'string', 'description': 'Token from a previous result'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'count': {'type': 'integer'}, 'videos': {'type': 'array'}, 'has_more': {'type': 'boolean'}, 'playlist': {'type': 'string'}, 'video_ids': {'type': 'array'}, 'next_page_token': {'type': 'string'}}, 'additionalProperties': True}
search_channel_videos
Search within a channel
Search videos inside one channel using YouTube's native relevance search. Results are ranked by relevance, so a video whose title lacks the query word is normal.
Read only
Open world
Input schema
{'type': 'object', 'required': [], 'properties': {'q': {'type': 'string', 'description': 'Query to search within the channel'}, 'name': {'type': 'string', 'description': '@handle, channel name, UC... channel id or channel URL'}, 'limit': {'type': 'integer', 'description': 'Results per page, 1-100 (default 30)'}, 'next_page_token': {'type': 'string', 'description': 'Token from a previous result'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'videos': {'type': 'array'}, 'channel': {'type': 'string'}, 'has_more': {'type': 'boolean'}, 'next_page_token': {'type': 'string'}}, 'additionalProperties': True}
search_playlist_videos
Search within a playlist
Find videos inside a playlist by a substring of the title (case-insensitive). YouTube has no native playlist search, so this scans up to 500 playlist items. truncated=true means there may be more matches beyond the scanned window.
Read only
Open world
Input schema
{'type': 'object', 'required': ['id', 'q'], 'properties': {'q': {'type': 'string', 'description': 'Substring to match in the video title'}, 'id': {'type': 'string', 'description': 'PL... playlist id or URL'}, 'limit': {'type': 'integer', 'description': 'Max matches to return, 1-100 (default 30)'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'truncated': {'type': 'boolean'}}, 'additionalProperties': True}
search_youtube
Search YouTube
Search YouTube for videos or channels. Paginate by passing next_page_token from the previous result. has_more tells you whether another page exists.
Read only
Open world
Input schema
{'type': 'object', 'required': [], 'properties': {'q': {'type': 'string', 'description': 'Search query (required unless paginating)'}, 'type': {'enum': ['video', 'channel'], 'type': 'string', 'description': "Default 'video'"}, 'limit': {'type': 'integer', 'description': 'Results per page, 1-50 (default 20)'}, 'next_page_token': {'type': 'string', 'description': 'Token from a previous result'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'has_more': {'type': 'boolean'}, 'next_page_token': {'type': 'string'}}, 'additionalProperties': True}
submit_transcripts_job
Submit transcripts batch
Queue transcripts for MANY videos at once (up to 4000) and get a job_id back immediately — the work continues in the background. Use this instead of calling get_transcript in a loop for more than a handful of videos. Feed it video ids from list_channel_videos or list_playlist_videos (ids_only=true). Next: poll get_transcripts_job until status is 'done', reading finished transcripts from get_transcripts_results as they land. Costs 1 credit per video, charged on submit; duplicates are removed first. Requires a user key (sk_...).
Open world
Input schema
{'type': 'object', 'required': ['videos'], 'properties': {'kind': {'enum': ['manual', 'auto'], 'type': 'string', 'description': 'Track kind. Omit to prefer a manual track and fall back to auto'}, 'lang': {'type': 'string', 'description': "Language code for every video, e.g. 'en'. Default 'en'."}, 'format': {'enum': ['text', 'json', 'srt', 'vtt', 'srv3'], 'type': 'string', 'description': "'text' = plain text (default), 'json' = timed segments, 'srt'/'vtt' = subtitle file body, 'srv3' = raw YouTube XML (srv3 does not combine with segment)"}, 'videos': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Video ids or URLs, up to 4000. Duplicates are collapsed.'}, 'segment': {'type': 'integer', 'maximum': 5000, 'minimum': 20, 'description': "Max characters per segment, for every video in the job. Raise it to 500-1500 when the transcripts are going into embeddings or retrieval. Left out, an auto-generated track is cut into ~180-character segments and a manual one keeps its author's own lines — so pass this when the whole job has to come back at one size."}, 'video_metadata': {'type': 'boolean', 'description': "Include each video's title, channel and duration alongside its transcript. Replaces a get_video_info call per video and costs nothing extra."}, 'idempotency_key': {'type': 'string', 'description': 'Optional. Resubmitting the same list with the same key returns the SAME job instead of opening a second one and charging twice.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'properties': {'count': {'type': 'integer'}, 'job_id': {'type': 'string'}, 'status': {'type': 'string'}, 'credits': {'type': 'object'}}, 'additionalProperties': True}
History
Recent tool changes
Added
get_credits
Sept. 17, 2026, 12:38 p.m.
Added
cancel_transcripts_job
Sept. 17, 2026, 12:38 p.m.
Added
get_transcripts_result
Sept. 17, 2026, 12:38 p.m.
Added
get_transcripts_results
Sept. 17, 2026, 12:38 p.m.
Added
get_transcripts_job
Sept. 17, 2026, 12:38 p.m.
Added
submit_transcripts_job
Sept. 17, 2026, 12:38 p.m.
Added
search_playlist_videos
Sept. 17, 2026, 12:38 p.m.
Added
list_playlist_videos
Sept. 17, 2026, 12:38 p.m.
Added
latest_channel_videos
Sept. 17, 2026, 12:38 p.m.
Added
search_channel_videos
Sept. 17, 2026, 12:38 p.m.
Added
list_channel_videos
Sept. 17, 2026, 12:38 p.m.
Added
search_youtube
Sept. 17, 2026, 12:38 p.m.
Added
get_video_info
Sept. 17, 2026, 12:38 p.m.
Added
get_transcript
Sept. 17, 2026, 12:38 p.m.
Discover
Similar MCP servers
Social Fetch
io.github.social-freak-ltd/socialfetch
Retrieves public content and metadata from social networks, music services, Facebook Marketplace, events, profiles, posts, commen…
Heista
co.heista/api
Analyzes video advertising, builds brand intelligence profiles, researches markets, and generates advertising scripts and creativ…
VarynForge
com.varynforge/server
Supports SEO research and content planning through niche analysis, competitor and keyword research, opportunity discovery, and wr…
Tmdb
io.github.pipeworx-io/tmdb
Provides TMDB-based movie, television, and people discovery, metadata, credits, recommendations, videos, and trend-related entert…
AfterLaunch: the agentic growth marketing engine
io.afterlaunch/agentic-growth-marketing
Runs growth-marketing workflows covering SEO, AI-search visibility, competitor analysis, content planning, distribution channels,…
Setlist Fm
io.github.pipeworx-io/setlist-fm
Provides setlist.fm concert research by artist, venue, city, country, and date, including artist records, concert histories, and …
Watchmode
io.github.pipeworx-io/watchmode
Searches streaming catalogs and availability across regions, services, genres, networks, titles, and release dates.
Vimeo
io.github.pipeworx-io/vimeo
Searches and retrieves public Vimeo videos, channels, categories, and related metadata.