"A server for searching YouTube" matching MCP tools:

• moderate_youtube_comment

  Hermoso

  Moderate a comment on the connected channel — the YouTube twin of moderate_meta_comment. ACTIONS: publish (make it visible again) · hold (hide it pending review) · reject (hide it as unfit for display) · spam (report it to YouTube — a REPORT, not a removal, so do not tell the user it is gone) · delete (permanent; YouTube has no undelete for a comment). hold, reject and publish are all reversible with each other, so only delete is confirm-gated. If the goal is just to take a comment out of public view, use reject rather than delete. banAuthor is valid ONLY with action="reject" — that is YouTube’s own restriction — and auto-rejects every future comment that author leaves on the channel. Get commentId from list_youtube_comments. 0 credits. Needs a connected YouTube channel.

  Connector

• youtube_shorts_transcript

  captapi

  Transcript for a YouTube Short — rejects long-form videos (≤3 min only). Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).

  Connector

• list_youtube_categories

  Hermoso

  List the video categories YouTube will accept on an upload in a given country. post_to_youtube takes a `categoryId` and this is the only way to discover a valid one — the id set AND the names differ by country, which is why regionCode is required rather than defaulted. Categories YouTube marks not-assignable are filtered out by default because an upload using one is refused. Read-only, 0 credits. Needs a connected YouTube channel.

  Connector

• get_transcript

  YouTube Transcript & Search MCP Server

  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.

  Connector

• youfiliate_disconnect_youtube

  Youfiliate Smart Links

  Disconnect your YouTube account from Youfiliate. IMPORTANT: Always confirm with the user before executing this action. The `confirm` parameter must be set to true. This removes stored OAuth tokens. You will need to reconnect to use the auto-migration feature. Does NOT modify any YouTube data or video descriptions. Common errors: - Not connected: no YouTube account to disconnect. - confirm=False: you must set confirm=True after getting user confirmation.

  Connector

• youtube_shorts_summarize

  captapi

  AI summary of a YouTube Short — rejects long-form videos (≤3 min only). Costs 3 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).

  Connector

• glim_web_fetch

  glim.sh

  Fetch a single web page and extract clean content. Auto-tier server-side: handles SSR (Next.js, Nuxt, TikTok, Pinterest, YouTube), SPA shells, PDFs, paywall detection, residential-proxy escalation, and stealth profiles for TikTok / Instagram / Pinterest / YouTube. Returns clean markdown (default) with a YAML frontmatter header (url, outcome, total_chars). Read 'outcome' to classify the result (success | teaser | thin_content | paywall | bot_challenge | consent_wall | login_wall | rate_limited | timeout | transient_upstream | unsupported_target | not_found | error). Large pages (>80k chars) are truncated inline with truncated_chars + a download_full_url to the complete extraction (expires ~1h). Permanently unsupported (outcome=unsupported_target, cost=0 upstream): Bluesky search, Instagram post/reel and tag/explore pages (profiles work), Pinterest search, g2.com, Truth Social, Xiaohongshu. Threads and Instagram profile pages ARE supported.

  Connector

• ic_research_ask

  Immersive Commons

  Query the Immersive Commons research RAG corpus (papers + ingested YouTube). Returns top-k chunks with similarity scores and source links. The query text is forwarded to a server-side RAG proxy (supercommons2 via Tailnet Funnel) and NEVER logged on the IC side — privacy contract. Use this for literature lookups, finding related work, surfacing citations the floor has already ingested. Args: { question: string (<=500 chars), k?: number (1-50, default 10), sources?: ('paper'|'book')[] (default ['paper']) }. Returns the upstream RAG response shape — typically { results: [{ paper_id, title, similarity, snippet, link }, ...] }. Required scope: research:query.

  Connector

• manage_youtube_playlist_image

  Hermoso

  PUT A CUSTOM COVER ON A PLAYLIST — the last call in a chain that already existed, since make_thumbnail renders the artwork and the playlist tools own the playlist. Without one YouTube shows the first video's thumbnail. action:'list' reads what is on a playlist, 'set' uploads a cover, 'delete' removes it. imageUrl must be a Hermoso-hosted URL, up to 50MB — a Hermoso render, a make_thumbnail result, or the user’s OWN artwork brought in with upload_file, which turns any local or external file into a URL this accepts. Nothing else is fetched server-side. YOUTUBE ANSWERS EVERY FAILURE HERE AS AN HTTP 500 "Internal error encountered" with the real reason buried inside it, so a plain relay would report a missing playlist id as a Hermoso outage — the refusals here are the real ones. If it comes back refused, the first thing to check is CHANNEL VERIFICATION: custom imagery needs a verified YouTube channel (add a phone number at youtube.com/verify), and on an unverified channel the sibling call that sets a custom video thumbnail is refused in the same way. Free.

  Connector

• youfiliate_rollback_migration

  Youfiliate Smart Links

  Roll back a completed migration, restoring original YouTube descriptions. IMPORTANT: This modifies YouTube video descriptions. Always confirm with the user before executing. This reverts all video descriptions to their pre-migration state. The rollback runs asynchronously. Requires a connected YouTube account. Common errors: - Migration not found or not in a rollback-eligible state. - YouTube not connected: reconnect first. - confirm=False: must set confirm=True after user confirmation.

  Connector

• post_to_youtube

  Hermoso

  Publish a finished video to the brand’s connected YouTube channel. Pass a Hermoso render URL (or an upload_file url for a local/external file). DEFAULTS TO UNLISTED (link-only — not on the channel, not searchable, but shareable by link AND usable as a YouTube/Google ad). Pass privacy:"public" to put it ON the channel (a public publish — confirm with the user first) or privacy:"private" for eyes-only. Do NOT use "private" for anything meant to run as an ad — private videos CANNOT be used as ads; unlisted is the ad-ready setting. SCHEDULE it with publishAt, FILE it under the right categoryId (the default 22 "People & Blogs" is wrong for most ads), SUBSCRIBER NOTIFICATIONS FOLLOW PRIVACY — a public publish announces the video to the channel’s subscribers (YouTube’s own default), while unlisted/private uploads stay quiet; pass notifySubscribers explicitly to override either way. Needs a connected YouTube channel (Settings ▸ Connectors ▸ YouTube).

  Connector

• polybridge_forecast

  PolyBridge

  Generate a read-only probability forecast for a clearly stated future event by searching relevant prediction markets and synthesizing evidence. Use when the user asks for a probability, outlook, or forecast; use polybridge_search when they only need market discovery. Does not place trades, provide financial advice, or access private/internal data.

  Connector

• youtube_shorts_comments

  captapi

  Comments on a YouTube Short — rejects long-form videos (≤3 min only). Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).

  Connector

• glim_youtube_get

  glim.sh

  Fetch a YouTube video transcript from a video URL or 11-char id. The transcript is cleaned server-side: deduplicated, tags/HTML stripped, with coarse [m:ss] timestamps - roughly a tenth the size of the raw captions. Default format='text' returns it inline (when it fits ~40K chars / ~10K tokens) so a single call gives you the text directly; long-form videos fall back to a download_url note. Pass format='json' for the same transcript plus transcript metadata (video_id, canonical url, language, origin, size) and a presigned download_url - for batch/programmatic use. Default origin='uploader_provided' (human captions); falls back to 'auto_generated' automatically if missing (counts as 2 upstream calls). Cached 7 days server-side.

  Connector

• manage_youtube_caption

  Hermoso

  Attach a real subtitle track to one of the connected channel’s videos, replace one, or delete one. Pass the caption file BODY itself as `text` (SRT or WebVTT), not a URL. `language` is required and may not be guessed — YouTube uses it to decide which viewers see the track. A track YouTube generated itself (trackKind ASR) is refused by name: YouTube owns it and it cannot be edited or deleted through any API; to replace it, upload your own track in the same language and YouTube prefers yours. Delete is confirm-gated — viewers with captions on lose them immediately and YouTube stops indexing the video by that text, though it can be re-uploaded if you still have the file. 0 credits. Needs a connected YouTube channel.

  Connector

• framefetch_search

  framefetch

  Search YouTube by keyword (yt-dlp, no login). Returns up to `limit` hits: url/title/uploader/durationSec/uploadDate(often null)/thumbnail/views. YouTube only — use framefetch_extract on a hit's url for transcript/frames/etc. Billed ~$0.002/call (metadata-tier), regardless of `limit`.

  Connector

• delete_youtube_report_job

  Hermoso

  Stop a YouTube bulk reporting job. IRREVERSIBLE IN A WAY THAT IS EASY TO MISS: the job IS the history — deleting it discards every daily CSV it has accumulated, and a replacement job starts over with only a 30-day backfill, so anything older than that is gone for good. Call WITHOUT confirm first: nothing is deleted and you get the real job read back from YouTube (its report type and when it was scheduled) to show the user. Then call again with confirm:true. Needs a connected YouTube channel.

  Connector

• update_youtube_channel

  Hermoso

  APPLY THE BRAND TO THE CHANNEL ITSELF — banner art, description, keywords, country and the trailer non-subscribers see. Every other YouTube tool brands the videos; this brands the page they sit on. Under the hood channels.update is a PUT, so the CURRENT settings are read and merged first — otherwise setting a description would silently wipe the channel's keywords, country and trailer. AND YOUTUBE SILENTLY IGNORES SOME FIELDS, channel title above all (usually only changeable in YouTube Studio): the result DIFFS what YouTube actually stored against what was asked for and reports anything that did not stick in `notApplied`. DO NOT REPORT THOSE AS CHANGED — a 200 is what YouTube accepted, not what it stored. A banner must be a Hermoso render (jpeg or png, under 6MB); YouTube re-crops it per device, so the safe area is the middle 1235x338 of a 2048x1152 image. Public and immediate — show the user what is going on the channel first. 0 credits. Needs YouTube connected.

  Connector

• youfiliate_connect_youtube

  Youfiliate Smart Links

  Initiate YouTube OAuth connection. Returns a URL the user must open in their browser. The user must open the returned URL in their web browser to authorize Youfiliate to access their YouTube channel. The OAuth callback is handled in the browser — this tool only returns the authorization URL. Does NOT read or modify any YouTube data. The OAuth flow is completed in the user's browser. Common errors: - Already connected: disconnect first with `youfiliate_disconnect_youtube`.

  Connector

• youtube.channel_search

  Vee3

  Search public videos on a YouTube channel by keyword or phrase. Accepts a bare channel id (for example UCJ5v_MCY6GNUBTO8-D3XoAg), not a URL. Returns matching video entries and cursorNext for pagination. Use cursorNext from a prior response as cursor for the next page. Cost = 10 tokens.

  Connector