HasData YouTube

Search YouTube and read video, channel and transcript data as JSON. No Google Cloud project.

使うべきか

品質と安全性

B
説明の品質
100%
スキーマの完全性
98%
命名の品質
30%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(10)

  • LOWTool 'hasdata_youtube_channel_getYoutubeChannel' doesn't follow camelCase/snake_casehasdata_youtube_channel_getYoutubeChannel 内
  • LOWTool 'hasdata_youtube_channel_getYoutubeChannel' name length outside 3-30 rangehasdata_youtube_channel_getYoutubeChannel 内
  • LOWTool 'hasdata_youtube_comments_getYoutubeComments' doesn't follow camelCase/snake_casehasdata_youtube_comments_getYoutubeComments 内
  • LOWTool 'hasdata_youtube_comments_getYoutubeComments' name length outside 3-30 rangehasdata_youtube_comments_getYoutubeComments 内
  • LOWTool 'hasdata_youtube_search_getYoutubeSearchResults' doesn't follow camelCase/snake_casehasdata_youtube_search_getYoutubeSearchResults 内
  • LOWTool 'hasdata_youtube_search_getYoutubeSearchResults' name length outside 3-30 rangehasdata_youtube_search_getYoutubeSearchResults 内
  • LOWTool 'hasdata_youtube_transcript_getYoutubeTranscript' doesn't follow camelCase/snake_casehasdata_youtube_transcript_getYoutubeTranscript 内
  • LOWTool 'hasdata_youtube_transcript_getYoutubeTranscript' name length outside 3-30 rangehasdata_youtube_transcript_getYoutubeTranscript 内
  • LOWTool 'hasdata_youtube_video_getYoutubeVideo' doesn't follow camelCase/snake_casehasdata_youtube_video_getYoutubeVideo 内
  • LOWTool 'hasdata_youtube_video_getYoutubeVideo' name length outside 3-30 rangehasdata_youtube_video_getYoutubeVideo 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~2,879トークン数(ツール定義)
~4.0 KB一般的なレスポンスサイズ
注意への影響は大きい(128k コンテキストの 2.25%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "youtube": {
      "command": "npx",
      "args": [
        "@hasdata/youtube-mcp"
      ]
    }
  }
}

実行可能なパッケージ

npm@hasdata/youtube-mcp1.0.9stdio
pypihasdata-youtube-mcp1.0.9stdio

リモートエンドポイント

https://mcp.hasdata.com/api/mcp?apis=youtubestreamable-http
https://mcp.hasdata.com/mcp?apis=youtubestreamable-http

できること

ツール一覧

ツール(5)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢hasdata_youtube_channel_getYoutubeChannel(channelId, tab, gl, hl, deviceType, ...)

Get YouTube Channel Data Fetches a YouTube channel by its ID (`UC…`) or handle (`@name`) and returns structured data for any channel tab — `featured`/Home, `videos`, `shorts`, `streams`, `playlists`, `posts`, `podcasts`, `releases`, `store` (desktop only), `about`. Returns channel identity (title, description, avatar, banner), subscriber count, country, join date, total-view count and social links (on the `about` tab), and the items on the requested tab (videos with views and publish date, playlists, posts, podcasts, etc.). Use to monitor competitor channels, build creator/brand directories, track posting cadence and growth signals, or feed `videoId` into the YouTube Video / Transcript endpoints.

入力スキーマ

{
  "type": "object",
  "properties": {
    "channelId": {
      "type": "string",
      "description": "YouTube channel identifier — either the canonical channel ID (`UC…`, 24 chars) or the public handle starting with `@` (e.g. `@PewDiePie`). Legacy `/c/<custom>` and `/user/<name>` URL slugs are also accepted."
    },
    "tab": {
      "type": "string",
      "enum": [
        "featured",
        "videos",
        "shorts",
        "streams",
        "playlists",
        "posts",
        "community",
        "podcasts",
        "releases",
        "about",
        "store"
      ],
      "description": "Channel tab to scrape. Each tab returns a different content shape:\n- `featured` (default) — channel Home page (channel trailer + curated rows)\n- `videos` — uploaded long-form videos\n- `shorts` — Shorts feed\n- `streams` — past and upcoming live streams\n- `playlists` — created and saved playlists\n- `posts` / `community` — community posts\n- `podcasts` — podcast episodes\n- `releases` — music releases\n- `about` — channel description, links, stats\n- `store` — channel merch\n"
    },
    "gl": {
      "type": "string",
      "description": "The two-letter country code for the country you want to limit the search to. Provide one exact documented value (245 allowed), e.g. `ac`, `af`."
    },
    "hl": {
      "type": "string",
      "description": "The two-letter language code for the language you want to use for the search. Provide one exact documented value (159 allowed), e.g. `af`, `ak`."
    },
    "deviceType": {
      "type": "string",
      "enum": [
        "desktop",
        "mobile"
      ],
      "description": "Device type for the request."
    },
    "paginationToken": {
      "type": "string",
      "description": "Token returned in the previous response to fetch the next page of results."
    }
  },
  "required": [
    "channelId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢hasdata_youtube_comments_getYoutubeComments(v, gl, hl, deviceType, nextPageToken)

Get YouTube Comments Returns a page of top-level `comments` for a YouTube video or short identified by its 11-character `videoId` (`v`). Each comment carries its text, author (name, channel id, avatar, verified/creator flags), publish time, and raw + normalized like and reply counts. `pagination` carries the returned comment `count`, the video's total comment count (`totalCount` as shown, `extractedTotalCount` as a number), a `nextPageToken`, and a `hasdataLink` that calls this endpoint for the next page. To page through comments pass the `nextPageToken` from the response back as the `nextPageToken` parameter (the token is self-contained — `v` is not needed on continuation requests). Use to mine video comments for sentiment, feedback or moderation, or to build comment datasets.

入力スキーマ

{
  "type": "object",
  "properties": {
    "v": {
      "type": "string",
      "description": "11-character YouTube video ID — the value of the `v=` query parameter in a watch URL (e.g. `dQw4w9WgXcQ` for `https://www.youtube.com/watch?v=dQw4w9WgXcQ`). Required for the first page; omit it on continuation requests that pass `nextPageToken`."
    },
    "gl": {
      "type": "string",
      "description": "The two-letter country code for the country you want to limit the search to. Provide one exact documented value (245 allowed), e.g. `ac`, `af`."
    },
    "hl": {
      "type": "string",
      "description": "The two-letter language code for the language you want to use for the search. Provide one exact documented value (159 allowed), e.g. `af`, `ak`."
    },
    "deviceType": {
      "type": "string",
      "enum": [
        "desktop",
        "mobile"
      ],
      "description": "Device type for the request."
    },
    "nextPageToken": {
      "type": "string",
      "description": "Token to fetch the next page of comments. Pass the `nextPageToken` from a previous response; omit it for the first page."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢hasdata_youtube_search_getYoutubeSearchResults(q, gl, hl, deviceType, sp, ...)

Get YouTube Search Results Searches YouTube for a query and returns the full results page split into `videoResults` (videoId, title, views, length, publish date, chapters, channel info, extensions like 4K/CC), `channelResults` (channelId, handle, subscribers, verified flag), `shortsResults` / `inlineShortsResults`, themed `shelves` (e.g. 'People also watched', 'Latest from <creator>'), `adsResults` and `sponsoredResults` (advertiser, landing URL, position), plus `searchInformation.totalResults`. Each block preserves its `positionOnPage` so the original layout is reconstructable. Use for competitor and topic monitoring, brand-mention tracking, ad-placement intelligence, creator discovery, trend research, or to feed `videoId` / `channelId` into the YouTube Video, Channel, or Transcript endpoints.

入力スキーマ

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free-text search query, exactly as a user would type it into the YouTube search box."
    },
    "gl": {
      "type": "string",
      "description": "The two-letter country code for the country you want to limit the search to. Provide one exact documented value (245 allowed), e.g. `ac`, `af`."
    },
    "hl": {
      "type": "string",
      "description": "The two-letter language code for the language you want to use for the search. Provide one exact documented value (159 allowed), e.g. `af`, `ak`."
    },
    "deviceType": {
      "type": "string",
      "enum": [
        "desktop",
        "mobile"
      ],
      "description": "Device type for the request."
    },
    "sp": {
      "type": "string",
      "description": "Raw YouTube `sp` filter token, copied verbatim from a YouTube search URL (e.g. `EgIQAQ%253D%253D`). When provided, it overrides `sortBy`, `date`, `videoType`, `length`, and `filters[]`. Use only if you need a YouTube-side filter that this API does not expose as a structured parameter."
    },
    "sortBy": {
      "type": "string",
      "enum": [
        "relevance",
        "popularity",
        "rating",
        "date",
        "views"
      ],
      "description": "Sort order applied to the results page. `relevance` (default) — best match for the query; `date` — newest first; `views` — most viewed first; `rating` — highest rated first; `popularity` — trending/most popular."
    },
    "date": {
      "type": "string",
      "enum": [
        "hour",
        "today",
        "week",
        "month",
        "year"
      ],
      "description": "Limit results to videos uploaded within this time window relative to now."
    },
    "videoType": {
      "type": "string",
      "enum": [
        "video",
        "shorts",
        "channel",
        "playlist",
        "movie"
      ],
      "description": "Restrict results to a single YouTube content type — regular videos, Shorts, channels, playlists, or movies."
    },
    "length": {
      "type": "string",
      "enum": [
        "under4",
        "between420",
        "plus20"
      ],
      "description": "Filter by video duration bucket:\n- `under4` — under 4 minutes\n- `between420` — 4 to 20 minutes\n- `plus20` — over 20 minutes\n"
    },
    "filters__": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "hd",
          "subtitles",
          "cc",
          "d3",
          "live",
          "bought",
          "k4",
          "d360",
          "location",
          "hdr",
          "vr180"
        ]
      },
      "description": "Feature flags to require on results. Multiple values are combined with AND (every flag must apply).\n\n- `hd` — HD quality\n- `k4` — 4K quality\n- `hdr` — HDR\n- `subtitles` — has subtitles/closed captions\n- `cc` — Creative Commons license\n- `d3` — 3D video\n- `d360` — 360° video\n- `vr180` — VR180 video\n- `live` — currently live\n- `bought` — purchased/paid content\n- `location` — has a geographic location tag\n"
    },
    "paginationToken": {
      "type": "string",
      "description": "Token returned in the previous response to fetch the next page."
    }
  },
  "required": [
    "q"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢hasdata_youtube_transcript_getYoutubeTranscript(v, languageCode, type)

Get YouTube Video Transcript Returns the timed transcript (subtitles) of a YouTube video by its 11-character `videoId`. `languageCode` selects the track (e.g. `en`, `de-DE`, `pt-BR`); `type=asr` requests the auto-generated speech-recognition track. Each segment in `transcript[]` carries `startMs`, `endMs`, `snippet`, and a formatted `startTimeText`. The response also includes `availableTranscripts[]` listing every track on the video (language name + code, `type: asr` for auto-generated, `selected: true` for the one returned) so callers can discover what else is available. Use to feed a video's spoken content into RAG/LLM pipelines, generate summaries or chapter outlines, build searchable archives, run translation or accessibility workflows, or analyze talking points across a creator's catalog (pair with the YouTube Channel endpoint to enumerate videos, then fetch transcripts).

入力スキーマ

{
  "type": "object",
  "properties": {
    "v": {
      "type": "string",
      "description": "11-character YouTube video ID — the value of the `v=` query parameter in a watch URL (e.g. `dQw4w9WgXcQ` for `https://www.youtube.com/watch?v=dQw4w9WgXcQ`)."
    },
    "languageCode": {
      "type": "string",
      "description": "BCP-47 / YouTube language code of the transcript track to return (e.g. `en`, `de`, `en-US`, `pt-BR`). Must match a track that the video actually has. When omitted, the video's default language track is returned."
    },
    "type": {
      "type": "string",
      "enum": [
        "asr"
      ],
      "description": "Set to `asr` to fetch the YouTube auto-generated (speech-recognition) track. Omit to fetch the human-authored track for `languageCode` when one exists."
    }
  },
  "required": [
    "v"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢hasdata_youtube_video_getYoutubeVideo(v, gl, hl, deviceType)

Get YouTube Video Data Fetches a single YouTube video by its 11-character `videoId`. Returns title, thumbnail, raw + normalized views and likes, `lengthSeconds`, publish date, category, keywords/tags, `isFamilySafe` / `isUnlisted` flags, the uploading channel (id, link, subscribers, avatar), the full description with parsed links and hashtags, available `captions` tracks (with `kind: asr` for auto-generated), Content-ID `music` matches (song/artist/album), creator `socialLinks`, and the `relatedVideos`, `endScreenVideos`, and `relatedShorts` rails, plus a `commentsLink` pointing at the YouTube Comments endpoint for this video. Use to enrich a video URL with metadata, monitor view/like growth, extract music or sponsor/affiliate links, gather features for recommender or RAG pipelines, or detect caption tracks before calling the YouTube Transcript endpoint.

入力スキーマ

{
  "type": "object",
  "properties": {
    "v": {
      "type": "string",
      "description": "11-character YouTube video ID — the value of the `v=` query parameter in a watch URL (e.g. `dQw4w9WgXcQ` for `https://www.youtube.com/watch?v=dQw4w9WgXcQ`)."
    },
    "gl": {
      "type": "string",
      "description": "The two-letter country code for the country you want to limit the search to. Provide one exact documented value (245 allowed), e.g. `ac`, `af`."
    },
    "hl": {
      "type": "string",
      "description": "The two-letter language code for the language you want to use for the search. Provide one exact documented value (159 allowed), e.g. `af`, `ak`."
    },
    "deviceType": {
      "type": "string",
      "enum": [
        "desktop",
        "mobile"
      ],
      "description": "Device type for the request."
    }
  },
  "required": [
    "v"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 5 件
検証済みバージョンは記録されていませんツール 5 件
検証済みバージョンは記録されていませんツール 4 件
検証済みバージョンは記録されていませんツール 4 件
検証済みバージョンは記録されていませんツール 4 件
検証済みバージョンは記録されていませんツール 4 件
検証済みバージョンは記録されていませんツール 4 件
検証済みバージョンは記録されていませんツール 4 件
検証済みバージョンは記録されていませんツール 4 件
認証が必要バージョンは記録されていません—