YouTube

Search, video, channel, playlist, comments, trending and related items from YouTube.

Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Search, video, channel, playlist, comments, trending and related items from YouTube. Hosted by the p

    How to connect

    How to connect YouTube to Claude

    The server address to paste into Claude settings:

    https://api.mcp.ai/p_youtube

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect YouTube to ChatGPT

    The server address to paste into ChatGPT settings:

    https://api.mcp.ai/p_youtube

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect YouTube to Cursor

    The server address to paste into Cursor settings:

    https://api.mcp.ai/p_youtube

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (35)

    Raw names from tools/list. Only developers need these.

    youtube_home_feedYouTube home feed (anonymous, geo/lang aware).
    youtube_trendingTrending videos by region.
    youtube_searchSearch videos, channels, playlists.
    youtube_resolve_urlResolve a YouTube URL or share link to its videoId / pageType.
    youtube_downloadStream/download metadata for a video (formats, audio/video URLs, status). Bulk support: accepts ids for batched execution.
    youtube_hypeYouTube Hype: viral / hyped videos feed.
    youtube_hashtagPosts under a hashtag (without leading #).
    youtube_playlistPlaylist items by playlist id. Bulk support: accepts ids for batched execution.
    youtube_commentsTop-level comments thread for a video. Bulk support: accepts ids for batched execution.
    youtube_video_relatedRelated videos for a given video id. Bulk support: accepts ids for batched execution.
    youtube_channel_homeChannel home page payload (featured shelves + meta). Bulk support: accepts ids for batched execution.
    youtube_channel_aboutChannel description, links, country, subscriber count, banner. Bulk support: accepts ids for batched execution.
    youtube_channel_videosChannel videos tab. Bulk support: accepts ids for batched execution.
    youtube_channel_shortsChannel shorts tab. Bulk support: accepts ids for batched execution.
    youtube_channel_playlistsChannel playlists tab. Bulk support: accepts ids for batched execution.
    youtube_channel_communityCommunity posts tab for a channel. Bulk support: accepts ids for batched execution.
    youtube_channel_featuredFeatured channels listed on a channel. Note: YouTube deprecated the featured-channels tab; this route exists upstream but typically returns an empty/error envelope. Bulk support: accepts ids for batched execution.
    youtube_channel_storeStore / merch shelf for a channel. Bulk support: accepts ids for batched execution.
    youtube_channel_searchSearch a channel's own videos and playlists. Bulk support: accepts ids for batched execution.
    youtube_channel_videos_postPOST variant of channel videos. Requires a `params` continuation token captured from a prior GET response — used to fetch deeper pages or filtered shelves that the GET surface can't address. Skip in daily smoke (no synthetic params). Bulk support: accepts ids for batched execution.
    youtube_channel_shorts_postPOST variant of channel shorts. Requires a `params` continuation token from a prior GET response. Skip in daily smoke (no synthetic params). Bulk support: accepts ids for batched execution.
    youtube_apiEscape hatch: call any path on the YouTube backend. Pass path (e.g. /search), optional method (default GET), query map, and JSON body for POST. Prefer the named youtube_* tools when available; this is for routes not in the manifest.
    youtube_my_channelsLista os canais do YouTube conectados (os que podem responder e moderar comentários), com id, nome e estatísticas. Use antes de responder para confirmar de qual canal a resposta vai sair. Custa 1 unidade da cota.
    youtube_comment_threadsComentários de TOPO pela API oficial, com as respostas já existentes. É daqui que sai o `parent_id` usado em youtube_comment_reply (o id do thread), então prefira esta tool a youtube_comments quando a intenção for responder. Sem `video_id`, traz os comentários do canal conectado inteiro (bom para 'o que ainda não respondi'). Custa 1 unidade da cota. Bulk support: accepts video_ids, channel_ids for batched execution.
    youtube_comment_replyResponde comentários como o canal conectado. Aceita VÁRIAS respostas numa chamada (`replies`), e um item que falha não derruba os outros. `parent_id` tem que ser o id de um comentário de TOPO (campo `id` do thread devolvido por youtube_comment_threads), nunca o id de uma resposta. Cada resposta consome 50 unidades da cota da API do YouTube, então responda o que importa em vez de varrer o canal.
    youtube_comment_postPublica um comentário NOVO de topo em um vídeo, como o canal conectado. Para responder alguém, use youtube_comment_reply. Custa 50 unidades da cota. Bulk support: accepts video_ids for batched execution.
    youtube_comment_updateEdita o texto de um comentário ou resposta PUBLICADO pelo canal conectado (corrigir um erro sem apagar e repostar, o que perderia as curtidas e o encadeamento). Só funciona em comentário de autoria do próprio canal. Custa 50 unidades da cota. Bulk support: accepts comment_ids for batched execution.
    youtube_comment_moderateModera comentários no canal conectado: publica (`published`), segura para revisão (`heldForReview`) ou rejeita (`rejected`). `ban_author` só é aceito junto de `rejected`. Vale apenas para comentários em vídeos do próprio canal. Custa 50 unidades por comentário.
    youtube_comment_deleteApaga DEFINITIVAMENTE um comentário (não tem desfazer). Só funciona em comentário do próprio canal ou em vídeo do canal conectado. Para esconder sem apagar, prefira youtube_comment_moderate com `rejected`. Custa 50 unidades da cota. Bulk support: accepts comment_ids for batched execution.
    show_versionShow the current MCP platform and adapter versions.
    report_bugReport a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
    connectReturns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
    toolkit_infoReturns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
    marketplaceThe official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
    authenticateMCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.