"A server for finding videos" matching MCP tools:

• get_channel_transcriptsA

  YouTube Transcript DownloaderA

  Get transcripts for a YouTube channel's most recent videos (newest first) as timestamped markdown, one section per video. Use for research across a creator's recent output; for one known video use get_transcript. Read-only; requires an API key. Charges 1 credit per video that returns a transcript, including repeat calls; videos without captions are skipped free. A 10-video call typically costs up to 10 credits, so start with a small limit. Rate limit: 5 requests per 10 seconds.

  ConnectorNo auth

• get_channel_transcriptsA

  YouTube Transcript DownloaderA

  Get transcripts for a YouTube channel's most recent videos (newest first) as timestamped markdown, one section per video. Use for research across a creator's recent output; for one known video use get_transcript. Read-only; requires an API key. Charges 1 credit per video that returns a transcript, including repeat calls; videos without captions are skipped free. A 10-video call typically costs up to 10 credits, so start with a small limit. Rate limit: 5 requests per 10 seconds.

  ConnectorNo auth

• tiktok_get_profileA

  Manifold MCPA

  One TikTok account: its follower count, its lifetime likes and how many videos it has posted. Use when: sizing a creator or a brand on TikTok, checking a handle is real, reading a bio before outreach. Not for: the account's videos, use tiktok_get_videos. Where its audience is, use tiktok_get_audience. Finding accounts by topic, use tiktok_search_videos and read the authors. Returns: Record. The account's handle, name, bio, verified, followers, following, posts_count, likes, views, website (the link in bio) and links, with other profile fields where TikTok fills them. null or empty = the platform does not publish it. Cost: 1 credit. Cached 24 hours. Example: {"handle": "@gymshark"}

  ConnectorAPI key

• tiktok_search_videosA

  Manifold MCPA

  TikTok videos matching a keyword, ranked by the platform's own search. Use when: "what is TikTok saying about X", finding creators in a category, watching a product or a brand name. Not for: one account's own videos, use tiktok_get_videos. A complete window of everything posted (TikTok search is ranked and never complete). Returns: List, ranked. rows[]: videos with author and author_followers, created_at, text (cut at 2000 characters), likes, comments, shares, saves, views, media, duration_s, links, transcript and top_comments[]. saves is how many people saved it, music the sound, and author_followers sizes each creator without another call. null or empty = the platform does not publish it. Cost: 1 credit per page. Cached 6 hours. Example: {"query": "creatine gummies", "since": "month", "sort": "popular"}

  ConnectorAPI key

• panda_delete_profileA

  Panda VideoB

  Delete a player profile. The default profile ('Padrão') cannot be deleted. A profile with no videos is deleted directly. A profile WITH videos needs `strategy` — ask the user which one: 'keep' = each video keeps its current look (gets its own copy of the profile's settings); 'migrate' = the videos move to `target_profile_id`. Up to 5 videos are processed immediately; more are queued (status 'pending') and the profile disappears once all videos are moved. If any video fails, the profile is NOT deleted.

  Connector

  Destructive

  No auth

• facebook_pageA

  SocialAPIsA

  Facebook pages: profile details, page ID, posts, videos, reels and photo albums. Actions: - action=details: Get a Facebook page's profile: name, category, follower and like counts, bio, contact info (email, phone, website, address), rating and the ad_page_id used by the Ads Library tools. Use it when you have the page URL; to find a page by name, use facebook_search (action=pages) first. Pricing: 1 credit per call; 5 credits when exact_followers_count=true. Inputs: link (required), exact_followers_count (optional). - action=id: Resolve a Facebook page URL to its numeric page ID. Use it when another tool needs a page or profile ID; use action=details for the page's data. Pricing: 1 credit per call. Inputs: link (required). - action=posts: List a Facebook page's recent posts, newest first, with text, media, reactions, comment and share counts. Returns 3-9 posts per call plus an end_cursor for the next page; filter by date with after_time / before_time. For reels or videos only, use action=reels or action=videos. Pricing: ceil(posts_returned / 3) credits per call, minimum 1. Inputs: link (required), limit (optional), end_cursor (optional), after_time (optional), before_time (optional), timezone (optional). - action=videos: List videos uploaded to a Facebook page, with video_id, title, duration, view count and thumbnail. Provide the page URL (link) or its numeric profile_id. Returns an end_cursor for the next page. For short-form reels, use action=reels. Pricing: 1 credit per call. Inputs: link (optional), profile_id (optional), limit (optional), end_cursor (optional). - action=reels: List a Facebook page's reels (short-form videos). Returns an end_cursor for the next page. For long-form videos, use action=videos. Pricing: 1 credit per call. Inputs: link (required), end_cursor (optional). - action=albums: List the photo albums of a Facebook page, with album_id, album_title, url, thumbnail_uri and album_items_count (text, e.g. "400 items"). Needs the numeric page ID (profile_id) from action=id. Returns an end_cursor for the next page. To get the photos in an album, pass its album_id to action=album_items. Pricing: 1 credit per call. Inputs: profile_id (required), limit (optional), end_cursor (optional). - action=album_items: Get the photos and videos inside a Facebook album (from a page or a group): media_id, media_type, url, thumbnail_uri and timestamp (Unix seconds). Needs an album_id from action=albums or facebook_group (action=albums). Returns an end_cursor for the next page. Pricing: 1 credit per call. Inputs: album_id (required), end_cursor (optional).

  ConnectorNo auth

• find_videosA

  KlyfA

  SEARCH the signed-in user's own YouTube catalogue and LIST the videos that match, by what is written in their titles, descriptions and tags. This is RETRIEVAL, not ranking: call it whenever the user wants to FIND or LIST videos rather than judge them. Use it for 'which of my videos are about X', 'show me every video where I talked about X', 'find my videos mentioning X', 'which videos have a referral or affiliate link in the description', 'list all my videos', 'what have I made about X', or any question whose answer is a SET of their videos. Also use it to pull ONE video's full record (its complete description, tags, length, views): pass that video's title as `video`. Leave everything empty to browse the whole library newest first. Results are paginated: each answer says how many matched and the `offset` to pass to see the next page, so keep asking to walk a large catalogue rather than stopping at the first page. It searches only what the creator WROTE, never what is spoken in the video. For how a video PERFORMED use analyze_video; for the best performers use find_best_videos. Needs no input: it reads their real connected YouTube channel directly. Never ask the creator anything first, not for context, not for a link, not for a title you could look up; call it immediately.

  ConnectorOAuth

• get_new_videosA

  TranscriptFetchA

  Read the new videos the account's monitors have found, newest first: titles, links and publish times, with their transcripts for monitors that deliver them. Leave monitor_id out for every monitor. To ask again later, pass this answer's lastEventId as since and only videos found after it come back. Monitors find videos when they check, on their own schedule (check_monitor_now checks at once). Found videos are kept for 30 days. Free.

  ConnectorAPI key

• tiktok_get_commentsA

  Manifold MCPA

  The comments on one TikTok video. Use when: reading what an audience actually said, finding objections and questions under a creator's post. Not for: comments across many videos (there is no such search on TikTok). The video itself, use tiktok_get_video. Returns: List. rows[]: one comment each: author, created_at, text (cut at 2000 characters), likes, replies, and parent_id and depth for a reply. Cost: 1 credit per page. Cached 6 hours. Example: {"url": "https://www.tiktok.com/@gymshark/video/7517114944362499342"}

  ConnectorAPI key

• bilibili_must_watchA

  Crawlora MCPB

  Fetch Bilibili's curated must-watch video collection. Use bilibili_popular for popularity-ranked videos, bilibili_ranking for charts, or bilibili_weekly for weekly picks.

  ConnectorNo auth

• bilibili_must_watchA

  Crawlora MCPB

  Fetch Bilibili's curated must-watch video collection. Use bilibili_popular for popularity-ranked videos, bilibili_ranking for charts, or bilibili_weekly for weekly picks.

  ConnectorNo auth

• goal-register-iteration-findingA

  Planner (proof-of-done)A

  Register an immutable LeanSolver finding against the currently tracked goal contract. subjectRefs must be goal-scoped refs of kind goal, criterion, or assumption. Returns the server-generated finding id to pass later as addressesFindingId; rejects stale contract tracking.

  ConnectorNo auth

• goal-register-iteration-findingA

  Planner MCP — provable "done" for AI agentsA

  Register an immutable LeanSolver finding against the currently tracked goal contract. subjectRefs must be goal-scoped refs of kind goal, criterion, or assumption. Returns the server-generated finding id to pass later as addressesFindingId; rejects stale contract tracking.

  ConnectorNo auth

• summarize_videoA

  TranscriptYTA

  Summary, key points, and timestamped study notes for a public YouTube video, generated from its transcript. Written in the transcript's language (translate_to changes which transcript is summarized). Costs 1 credit for the transcript plus 1 for the summary (2 total) for most videos; long videos cost about 1 more per further 45 minutes.

  ConnectorNo auth

• panda_action_apply_profile_to_folderA

  Panda VideoB

  Deterministically resolve a player profile and a folder and link the profile to ALL videos of the folder in one call (sends folder_id, like the dashboard). Subfolders are not included; videos in any status (not only converted ones) also receive the profile. Videos with their own customized player lose that customization. The work is queued: the result is status 'executed' with api_status 'pending' — confirm later with panda_get_profile (videos_count). api_status 'ok' only means the API found no videos in the folder: nothing was changed. Free action (no credits). dry_run=true (default) returns a preview.

  ConnectorNo auth

• own_video_exportA

  Video GrabA

  Use this when the user wants to export or download videos they uploaded themselves to TikTok, YouTube, Instagram or X. Pass the platform, for example {"platform": "youtube"}. Returns the official steps in order, their limits and the help_url to quote. It does not sign in or fetch the video. Not for any other platform, such as Douyin, Bilibili or Xiaohongshu: no export steps are offered here, so do not call it; tell the user to use that platform's own account settings. Not for someone else's video or for finding footage (use search_free_videos). We do not rip videos from social platforms or remove watermarks.

  ConnectorNo auth

• list_videosA

  Skool by CotletA

  Videos in the group's Classroom lessons and feed posts, uploaded or linked. Lists the videos this account can watch: one per Classroom lesson with a video, in course order, and the videos in the newest feed posts (post_pages pages of 30). An uploaded video has a video_id and transcript true: pass it with its course_id and lesson_id, or post_id, to get_video_transcript. A linked one (YouTube, Vimeo, Loom, Wistia) has only video_url. Locked courses are named in locked_courses, without their videos.

  ConnectorNo auth

• tiktok_profileA

  ReachSocial - One API for social media data.A

  Retrieve normalized public TikTok profile metadata. Use for one account's public profile metadata. For its posts/videos, use tiktok_feed. Returns profile metadata without retaining avatars or videos. An entitled B2B API key executes immediately under the client's billing and spending limits. OAuth requires an approved owner wallet connection and creates a $0.05 USDC payment request on Base; execution waits for browser approval/payment. Then use get_reachsocial_request with the returned request_id. Preserve the idempotency_key for retries; changed input needs a new key. Invalid/private/unavailable targets and access, rate, or spend limits return errors.

  ConnectorAPI key

• panda_list_hls_encrypted_videosA

  Panda VideoB

  List the account's videos that are already encrypted (HLS). Videos still in an encryption batch only show up when it finishes (see panda_get_hls_encryption_batches). Returns {total, page, limit, pages, videos: [{id, title, status, folder_id, encrypted_at, available_resolutions, ...}]}. Default 25 videos per page, max 50; keep calling with page+1 while page < pages.

  ConnectorNo auth

• search_youtubeA

  YouTube Transcript + YouTube Search MCPA

  Use this when the user wants to find YouTube videos or channels on a topic, for example 'find lectures on linear algebra' or 'popular videos about the Apollo missions', before reading or comparing them. Returns each result's title, video ID, link, channel, views, length, and upload date. Pass `continuation` from a previous response for the next page. Does not return what a video says: call get_youtube_transcript with a result's video ID for that.

  ConnectorOAuth

• list_channel_videosA

  YouTube Transcript + YouTube Search MCPA

  Use this when the user wants to browse a YouTube channel's uploads beyond its latest videos, for example to see a creator's older episodes, its most popular videos, its Shorts, or its past live streams. Returns the channel's uploads one page at a time. `tab` picks Videos (default), Shorts or Live; `sort` picks latest (default), popular or oldest. Both apply to the first page only. Pass `continuation` from a previous response for the next page.

  ConnectorOAuth