此 MCP 可以做什么
Searches and retrieves YouTube videos, channels, playlists, comments, feeds, trends, and related media, with tools for channel comment management.
功能
工具
35
工具
authenticate
MCP.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.
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'token': {'type': 'string'}}}
connect
Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
marketplace
The official mcp.ai marketplace â 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 â describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id â invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed â 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.
可访问外部资源
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'number', 'default': 10}, 'query': {'type': 'string', 'default': ''}, 'action': {'enum': ['search', 'describe', 'install', 'uninstall', 'subscribe', 'cancel', 'resume', 'report_bug', 'request_mcp', 'list_tools', 'invoke', 'search_prompts', 'get_prompt', 'publish_prompt'], 'type': 'string', 'default': 'search'}, 'mcp_id': {'type': 'string', 'default': ''}, 'message': {'type': 'string', 'default': ''}, 'tool_id': {'type': 'string', 'default': ''}, 'arguments': {'type': 'string', 'default': '{}'}, 'immediate': {'type': 'boolean', 'default': False}, 'tier_slug': {'type': 'string', 'default': ''}, 'prompt_body': {'type': 'string', 'default': ''}, 'prompt_slug': {'type': 'string', 'default': ''}, 'prompt_tool': {'type': 'string', 'default': ''}, 'prompt_vars': {'type': 'string', 'default': '{}'}, 'conversation': {'type': 'string', 'default': '[]'}, 'prompt_title': {'type': 'string', 'default': ''}, 'request_name': {'type': 'string', 'default': ''}, 'cancel_reason': {'enum': ['too_expensive', 'missing_features', 'switched_service', 'unused', 'customer_service', 'too_complex', 'low_quality', 'other'], 'type': 'string'}, 'cancel_comment': {'type': 'string', 'default': ''}, 'prompt_targets': {'type': 'array', 'items': {'enum': ['claude', 'chatgpt', 'cursor', 'lovable'], 'type': 'string'}, 'default': []}, 'report_context': {'type': 'string', 'default': ''}, 'prompt_category': {'type': 'string', 'default': ''}, 'request_details': {'type': 'string', 'default': ''}, 'prompt_description': {'type': 'string', 'default': ''}}}
report_bug
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['message'], 'properties': {'context': {'type': 'string', 'default': ''}, 'message': {'type': 'string'}, 'conversation': {'type': 'string', 'default': '[]'}}}
show_version
Show the current MCP platform and adapter versions.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
toolkit_info
Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
youtube_api
Escape 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.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['path'], 'properties': {'body': {}, 'path': {'type': 'string'}, 'query': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'anyOf': [{'type': 'string'}, {'type': 'number'}, {'type': 'boolean'}]}}, 'method': {'enum': ['GET', 'HEAD', 'POST', 'PUT', 'PATCH', 'DELETE'], 'type': 'string'}}}
youtube_channel_about
Channel description, links, country, subscriber count, banner.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'forUsername': {'type': 'string'}}}
youtube_channel_community
Community posts tab for a channel.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_channel_featured
Featured channels listed on a channel. Note: YouTube deprecated the featured-channels tab; this route exists upstream but typically returns an empty/error envelope.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_channel_home
Channel home page payload (featured shelves + meta).
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_channel_playlists
Channel playlists tab.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'sort_by': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_channel_search
Search a channel's own videos and playlists.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'query': {'type': 'string'}, 'token': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_channel_shorts
Channel shorts tab.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_channel_shorts_post
POST 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.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['params'], 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'params': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_channel_store
Store / merch shelf for a channel.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'forUsername': {'type': 'string'}}}
youtube_channel_videos
Channel videos tab.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'sort_by': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_channel_videos_post
POST variant of channel videos. Requires a `params` continuation token captured from a prior GET response â used to fetch deeper pages or filtered shelves that the GET surface can't address. Skip in daily smoke (no synthetic params).
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['params'], 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'params': {'type': 'string'}, 'forUsername': {'type': 'string'}}}
youtube_comment_delete
Apaga DEFINITIVAMENTE um comentário (não tem desfazer). Só funciona em comentário do próprio canal ou em vÃdeo 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.
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['comment_id'], 'properties': {'account': {'type': 'string'}, 'comment_id': {'type': 'string'}, 'comment_ids': {'type': 'array', 'items': {'type': 'string'}}}}
youtube_comment_moderate
Modera comentários no canal conectado: publica (`published`), segura para revisão (`heldForReview`) ou rejeita (`rejected`). `ban_author` só é aceito junto de `rejected`. Vale apenas para comentários em vÃdeos do próprio canal. Custa 50 unidades por comentário.
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['comment_ids', 'status'], 'properties': {'status': {'enum': ['published', 'heldForReview', 'rejected'], 'type': 'string'}, 'account': {'type': 'string'}, 'ban_author': {'type': 'boolean'}, 'comment_ids': {'type': 'array', 'items': {'type': 'string'}}}}
youtube_comment_post
Publica um comentário NOVO de topo em um vÃdeo, como o canal conectado. Para responder alguém, use youtube_comment_reply. Custa 50 unidades da cota.
Bulk support: accepts video_ids for batched execution.
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['video_id', 'text'], 'properties': {'text': {'type': 'string'}, 'account': {'type': 'string'}, 'video_id': {'type': 'string'}, 'video_ids': {'type': 'array', 'items': {'type': 'string'}}}}
youtube_comment_reply
Responde comentários como o canal conectado. Aceita VÃRIAS respostas numa chamada (`replies`), e um item que falha não derruba os outros. `parent_id` tem que ser o id de um comentário de TOPO (campo `id` do thread devolvido por youtube_comment_threads), nunca o id de uma resposta. Cada resposta consome 50 unidades da cota da API do YouTube, então responda o que importa em vez de varrer o canal.
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['replies'], 'properties': {'account': {'type': 'string'}, 'replies': {'type': 'array', 'items': {'type': 'object', 'required': ['parent_id', 'text'], 'properties': {'text': {'type': 'string'}, 'parent_id': {'type': 'string'}}}}}}
youtube_comments
Top-level comments thread for a video.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}, 'sort_by': {'type': 'string'}}}
youtube_comment_threads
Comentários de TOPO pela API oficial, com as respostas já existentes. à daqui que sai o `parent_id` usado em youtube_comment_reply (o id do thread), então prefira esta tool a youtube_comments quando a intenção for responder. Sem `video_id`, traz os comentários do canal conectado inteiro (bom para 'o que ainda não respondi'). Custa 1 unidade da cota.
Bulk support: accepts video_ids, channel_ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'order': {'enum': ['time', 'relevance'], 'type': 'string'}, 'account': {'type': 'string'}, 'video_id': {'type': 'string'}, 'video_ids': {'type': 'array', 'items': {'type': 'string'}}, 'channel_id': {'type': 'string'}, 'page_token': {'type': 'string'}, 'channel_ids': {'type': 'array', 'items': {'type': 'string'}}, 'max_results': {'type': 'number'}, 'search_terms': {'type': 'string'}, 'moderation_status': {'enum': ['heldForReview', 'likelySpam', 'published'], 'type': 'string'}}}
youtube_comment_update
Edita 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.
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['comment_id', 'text'], 'properties': {'text': {'type': 'string'}, 'account': {'type': 'string'}, 'comment_id': {'type': 'string'}, 'comment_ids': {'type': 'array', 'items': {'type': 'string'}}}}
youtube_download
Stream/download metadata for a video (formats, audio/video URLs, status).
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'cgeo': {'type': 'string'}}}
youtube_hashtag
Posts under a hashtag (without leading #).
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['tag'], 'properties': {'tag': {'type': 'string'}, 'type': {'type': 'string'}, 'token': {'type': 'string'}}}
youtube_home_feed
YouTube home feed (anonymous, geo/lang aware).
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'geo': {'type': 'string'}, 'lang': {'type': 'string'}, 'token': {'type': 'string'}}}
youtube_hype
YouTube Hype: viral / hyped videos feed.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'geo': {'type': 'string'}, 'lang': {'type': 'string'}, 'token': {'type': 'string'}}}
youtube_my_channels
Lista os canais do YouTube conectados (os que podem responder e moderar comentários), com id, nome e estatÃsticas. Use antes de responder para confirmar de qual canal a resposta vai sair. Custa 1 unidade da cota.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'account': {'type': 'string'}}}
youtube_playlist
Playlist items by playlist id.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}}}
youtube_resolve_url
Resolve a YouTube URL or share link to its videoId / pageType.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['url'], 'properties': {'url': {'type': 'string'}}}
youtube_search
Search videos, channels, playlists.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'geo': {'type': 'string'}, 'lang': {'type': 'string'}, 'type': {'type': 'string'}, 'query': {'type': 'string'}, 'token': {'type': 'string'}, 'sort_by': {'type': 'string'}, 'duration': {'type': 'string'}, 'upload_date': {'type': 'string'}}}
youtube_trending
Trending videos by region.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'geo': {'type': 'string'}, 'lang': {'type': 'string'}, 'type': {'type': 'string'}}}
youtube_video_related
Related videos for a given video id.
Bulk support: accepts ids for batched execution.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string'}, 'ids': {'type': 'array', 'items': {'type': 'string'}}, 'token': {'type': 'string'}}}
历史
近期工具变更
已添加
authenticate
2026年9月17日 12:45
已添加
marketplace
2026年9月17日 12:45
已添加
toolkit_info
2026年9月17日 12:45
已添加
connect
2026年9月17日 12:45
已添加
report_bug
2026年9月17日 12:45
已添加
show_version
2026年9月17日 12:45
已添加
youtube_comment_delete
2026年9月17日 12:45
已添加
youtube_comment_moderate
2026年9月17日 12:45
已添加
youtube_comment_update
2026年9月17日 12:45
已添加
youtube_comment_post
2026年9月17日 12:45
已添加
youtube_comment_reply
2026年9月17日 12:45
已添加
youtube_comment_threads
2026年9月17日 12:45
已添加
youtube_my_channels
2026年9月17日 12:45
已添加
youtube_api
2026年9月17日 12:45
已添加
youtube_channel_shorts_post
2026年9月17日 12:45
已添加
youtube_channel_videos_post
2026年9月17日 12:45
已添加
youtube_channel_search
2026年9月17日 12:45
已添加
youtube_channel_store
2026年9月17日 12:45
已添加
youtube_channel_featured
2026年9月17日 12:45
已添加
youtube_channel_community
2026年9月17日 12:45
已添加
youtube_channel_playlists
2026年9月17日 12:45
已添加
youtube_channel_shorts
2026年9月17日 12:45
已添加
youtube_channel_videos
2026年9月17日 12:45
已添加
youtube_channel_about
2026年9月17日 12:45
已添加
youtube_channel_home
2026年9月17日 12:45
已添加
youtube_video_related
2026年9月17日 12:45
已添加
youtube_comments
2026年9月17日 12:45
已添加
youtube_playlist
2026年9月17日 12:45
已添加
youtube_hashtag
2026年9月17日 12:45
已添加
youtube_hype
2026年9月17日 12:45
发现
类似的 MCP 服务器
Social Fetch
io.github.social-freak-ltd/socialfetch
Retrieves public content and metadata from social networks, music services, Facebook Marketplace, events, profiles, posts, commen…
TopTik — TikTok data
app.toptik/tiktok
Provides TikTok creator, video, hashtag, sound, live-stream, comment, transcript, place, and discovery data.
youtube
com.jojapi/youtube
Provides YouTube search, channel, playlist, video, community, comments, trending, and related-content data, plus channel video pu…
Heista
co.heista/api
Analyzes video advertising, builds brand intelligence profiles, researches markets, and generates advertising scripts and creativ…
API Direct
io.apidirect/api-direct
Searches and retrieves data from social networks, news and Google services, while also providing Amazon product, seller, ranking,…
TERM
app.term/forum
Provides an agent-oriented forum for publishing findings, discussing questions, voting, communities, and deterministic research c…
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…