YouTube MCP server for your agent

To give Claude, Cursor, ChatGPT or another MCP client YouTube data, add Apify's hosted MCP server with the Actors ticked below as tools (6 by default); the URL is in every config. Sign in with your Apify account or pass an API token; each call runs the Actor and returns YouTube records to the agent.

One click, signs in with Apify on first use:

Add to Cursor Add to VS Code

Any other client, one command (writes the config for 25+ agents, including Windsurf, Zed, Cline and Goose):

npx add-mcp "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/youtube-channel-video-catalog-and-profile-scraper,nimbryxo-studio/youtube-video-comment-and-reply-thread-scraper,nimbryxo-studio/youtube-caption-and-whisper-ai-transcript,vexaloom-labs/youtube-search-results-and-entity-type-scraper,vexaloom-labs/youtube-video-metadata-and-chapter-extractor,nimbryxo-studio/youtube-trending-feed-extractor-by-category" --name apify-youtube
Catalogue Actors
17
In this bundle
6
Official API
Public
Data checked
2026-11-12

Config for your client

Claude Code configterminal or .mcp.json

claude mcp add --transport http apify-youtube "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/youtube-channel-video-catalog-and-profile-scraper,nimbryxo-studio/youtube-video-comment-and-reply-thread-scraper,nimbryxo-studio/youtube-caption-and-whisper-ai-transcript,vexaloom-labs/youtube-search-results-and-entity-type-scraper,vexaloom-labs/youtube-video-metadata-and-chapter-extractor,nimbryxo-studio/youtube-trending-feed-extractor-by-category"
  1. Run the command in your project folder. Add --scope user to make it available in every project.
  2. Start Claude Code, type /mcp, pick the server and sign in to Apify in the browser window.
  3. No browser sign-in? Add --header "Authorization: Bearer YOUR_APIFY_TOKEN" to the command instead.

Sign-in: OAuth sign-in on first use, or a token header.

Validated, not executed: 7 of 7 checks pass
  • Uses Apify's hosted MCP endpoint over HTTPS
  • The tools parameter lists exactly the chosen Actors as owner/name
  • JSON configs parse and use the client's top-level key and the same URL
  • Codex TOML has a [mcp_servers.<name>] table with url and bearer_token_env_var
  • CLI commands quote the same URL and use the streamable HTTP transport
  • One-click install links decode back to the same URL and carry no token
  • Only placeholders, no real token

Official API or an Actor?

YouTube has a public official API

The Data API exposes public video, channel, playlist and comment data. Each project receives a daily quota measured in units.

No per-call fee is published; the constraint is the daily quota. Extra quota is not self-serve.

The default allocation is 100 search.list calls per day, 100 videos.insert calls per day, and 10,000 quota units per day combined for other endpoints. Captions for videos you do not own are not available through the API.

YouTube Data API v3 documentation

Use the API and public pages within YouTube's terms; transcripts are not an official public API; not legal advice.

Where it stops

The token-based configurations require your own Apify API token through APIFY_TOKEN; the hosted endpoint URL alone does not authenticate you. These configurations do not set up YouTube OAuth or grant access to a signed-in YouTube account, and Recipe for Agents has not authenticated Apify or YouTube for you. YouTube’s public Data API is another route for video, channel, playlist and comment records, subject to project quota.

Every YouTube Actor in the catalogue

ActorReturnsFieldsStore priceLast update
YouTube Channel About, Playlists & Posts Finder Channel profile rows with About details, external links, and optional nested surfaces, plus one-row-per-playlist and… Fields include channelName, title, handle. 20 $0.99 per 1,000 results 2026-11-07
YouTube Channel Video Catalog & Profile Scraper YouTube channel profile metadata and video, Shorts, playlist, podcast, course, release, and live-stream rows with exact views, likes, and… Fields include title, videoId, viewCount. 49 $0.99 per 1,000 results 2026-10-18
YouTube Channel Video Feed Quick Scraper One row per video with recordType/sourceUrl, exact publish date, like count, category, tags, optional comment count, view/like metrics… Fields include title, videoId, viewCount. 52 $0.99 per 1,000 results 2026-11-09
YouTube Community Tab Post & Poll Scraper Community posts with exact dates, engagement, images, polls, quizzes, playlists, reposts and comment threads, plus one-row-per-comment… Fields include postId, postType, channelName. 7 $0.99 per 1,000 results 2026-10-23
YouTube Hashtag Video & Shorts Ranking Scraper Videos and Shorts ranked under the requested hashtags, with view count, channel info and hashtag totals. Fields include hashtag, videoId, title. 40 $0.99 per 1,000 results 2026-11-05
YouTube Live Stream & Replay Chat Extractor Chat events with authors, replay offsets, Super Chat and gift amounts, membership detail, badges, stream metadata and optional summaries. Fields include videoId, eventType, authorName. 15 $0.99 per 1,000 results 2026-11-03
YouTube Playlist Contents & Channel Playlist Finder Playlist video rows with exact views, likes, publish dates and unavailable placeholders, plus channel collection and playlist-search rows. Fields include title, videoId, playlistTitle. 47 $0.99 per 1,000 results 2026-10-31
YouTube Search Results & Entity Type Scraper Search result rows for videos, Shorts, channels, playlists, and movies, with optional exact dates, views, likes, categories, tags, and… Fields include videoId, title, channelName. 42 $0.99 per 1,000 results 2026-10-22
YouTube Search Suggestions Scraper Autocomplete suggestion rows with seed, expansion type, rank, locale, source, search URL and channel/topic metadata when available. Fields include suggestion, seed, locale. 8 $0.99 per 1,000 results 2026-11-10
YouTube Shorts Metadata Extractor for Channels & Hashtags YouTube Shorts with exact view, like, comment, date, duration, category and sound metadata, scraped by channel, hashtag, keyword search or… Fields include title, videoId, viewCount. 38 $0.99 per 1,000 results 2026-10-19
YouTube SponsorBlock Segments Scraper SponsorBlock segment rows, per-video/run summaries, and truthful per-video status rows. Fields include videoId, category, actionType. 41 $0.99 per 1,000 results 2026-11-05
YouTube Trending Feed Extractor by Category & Market Ranked YouTube chart entries and category-hub videos with rank movement, exact video details and status rows. Fields include sourceName, title, channelName. 70 $0.99 per 1,000 results 2026-11-02
YouTube Video Comment & Reply Thread Scraper Flat comment and reply rows with author identity, rounded engagement counts, honest approximate dates, thread fields, video statistics… Fields include commentId, authorName, text. 24 $0.99 per 1,000 results 2026-10-24
YouTube Video Metadata & Chapter Extractor One record per video with exact metadata, manual and automatic chapters, heatmap segments, caption-track availability, live and age… Fields include videoId, title, channelName. 60 $0.99 per 1,000 results 2026-10-26
YouTube Video, Playlist & Channel Downloader with Metadata YouTube video metadata, media files, captions, transcripts, and honest failure rows. Fields include video_url, title, uploader. 20 $0.99 per 1,000 results 2026-10-24
YouTube Caption & Whisper AI Transcript Extractor One record per video with its transcript (segments, full text, SRT/VTT, optional word timings), caption/translation metadata, chapters… Fields include video_id, title, channel_name. 31 $0.99 per 1,000 results 2026-10-21
YouTube Channel Contact Email Finder Dataset of YouTube channel contact records with channel metadata, public emails and their sources, links, socials, and hidden-email flags. Fields include channelId, handle, name. 16 $0.99 per 1,000 results 2026-10-26

Call these Actors from code: the YouTube data API page

Store links: youtube-channel-about-playlists-and-posts-finder, youtube-channel-video-catalog-and-profile-scraper, youtube-channel-video-feed-quick-scraper, youtube-community-tab-post-and-poll-scraper, youtube-hashtag-video-and-shorts-ranking-scraper, youtube-live-stream-and-replay-chat-extractor, youtube-playlist-contents-and-channel-playlist, youtube-search-results-and-entity-type-scraper, youtube-search-suggestions-scraper, youtube-shorts-metadata-extractor-for-channels, youtube-sponsorblock-segments-scraper, youtube-trending-feed-extractor-by-category, youtube-video-comment-and-reply-thread-scraper, youtube-video-metadata-and-chapter-extractor, youtube-video-playlist-and-channel-downloader, youtube-caption-and-whisper-ai-transcript, youtube-channel-contact-email-finder

YouTube recipes for n8n

Troubleshooting

Why does the client say Unauthorized or invalid token?

Every Apify Actor tool needs a signed-in Apify account. Reconnect the server so the OAuth sign-in runs again, or switch to the token variant: an Authorization: Bearer header with an API token from Apify Console, Settings, API and integrations. For a local server the token must be in the server's own env block, not only in your shell.

Source: Apify MCP server README

Why did my agent's tool list change after an update?

Without a tools parameter Apify's server loads its default tool set, which changes between releases. The URLs on this site pin the tools with ?tools=, so the agent always gets the same Actor tool plus fetch-actor-details. Apify's README gives the same advice for production.

Source: Apify MCP server README

What happens when the agent sends input the Actor rejects?

The server answers with the Actor's input schema, so the agent can fix the arguments and call again. The fetch-actor-details tool in every scoped URL lets it read that schema before the first call.

Source: Apify MCP server README

Claude Code shows Needs authentication. Why?

The server is added but not signed in. Type /mcp in an interactive session and authenticate, or run claude mcp login with the server name. Headless runs with claude -p cannot complete OAuth, so sign in once interactively or use the --header token variant.

Source: Claude Code MCP documentation

Claude Code warns that a tool result is too large. What can I change?

Claude Code warns above 10,000 tokens of tool output and caps it at 25,000 by default (MAX_MCP_OUTPUT_TOKENS raises it). Ask the agent for fewer results per call, for example a lower result limit for the Actor.

Source: Claude Code MCP documentation

Cursor does not show the server's tools. What should I check?

Open the Output panel and pick MCP Logs to see the connection error. A deeplink install that does nothing usually means an older Cursor build; update it or paste the JSON into mcp.json by hand.

Source: Cursor MCP documentation

Every fix in one place

Questions

How do I get YouTube data into Claude?

Add the Apify MCP configuration for Claude Desktop or Claude Code and complete Apify authentication in your client. Ask Claude to inspect the chosen Actor’s published schema, collect the relevant public records and return source links.

Can Claude get YouTube transcripts with this connection?

The listed Actors document channel, video, post, playlist, search and chat records, without establishing transcript or caption output. Spoken-content summaries need a separate transcript source.

Do I need to sign in to YouTube or use OAuth?

The configurations do not set up YouTube OAuth, and an Apify token does not sign you into YouTube. You must authenticate Apify yourself; Recipe for Agents has not authenticated either service for you.

How do I make Claude search YouTube or read a playlist?

Add YouTube Search Results & Entity Type Scraper or YouTube Playlist Contents & Channel Playlist Finder to the MCP tool list, since neither appears in the ready-to-copy configurations. Then ask Claude to inspect the selected Actor’s inputs before collecting search results or playlist contents.