MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者による説明(英語の原文)
ASO for your AI: keywords, rankings, competitors and ads across 2.5M+ App Store apps.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
Authorization必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
このアドレスはリクエストの header にキーが必要ですが、コネクタを追加するメニューでは設定できません。代わりにClaude Code、Cursor、VS Codeを使ってください。
ターミナルでこれを実行します
claude mcp add --transport http asonix https://api.asonix.io/mcp --header 'Authorization: Bearer {token}'動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"asonix": {
"url": "https://api.asonix.io/mcp",
"headers": {
"Authorization": "Bearer {token}"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"asonix": {
"type": "http",
"url": "https://api.asonix.io/mcp",
"headers": {
"Authorization": "Bearer {token}"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
このアドレスはリクエストの header にキーが必要ですが、コネクタを追加するメニューでは設定できません。代わりにClaude Code、Cursor、VS Codeを使ってください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
Authorization 必須 HTTP headerこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
ツールの名前と説明は、サーバーが2026年11月6日に返したそのままの内容です。書いたのは作者で、私たちではありません。プレーンテキストとして表示しています。
get_ai_visibility_overviewRead a tracked app's stored AI recommendation benchmark: coverage, mention/recommendation/App Store citation rates, weekly history and topic/prompt summaries with run IDs. Not ASO visibility. No collection or model calls. Defaults to four weeks; no benchmark returns NOT_STARTED.
get_ai_visibility_reasonsRead cached recommendation themes, exact answer quotes and description passage matches. Includes analysis status, timestamps and its own evidence denominator (which can differ from the overview). No generation or refresh. Full descriptions stay in get_app_overview; this returns m
get_ai_visibility_evidenceRead a saved AI Visibility answer by runId, or recent answers for one promptId (exactly one required). Defaults to one run; use nextBefore for older prompt runs. Citations, resolved mentions and classification coverage are included. includeTrace adds captured searches; their sour
add_appAdd an App Store app to the current Asonix workspace by App Store ID or app name/search query.
create_unreleased_appCreate a private unreleased app idea in the current Asonix workspace. Use this when the user's app is not on the App Store yet; then add researched keywords with add_keywords.
search_appsFind App Store apps by name or developer, to get an app's appStoreId; use it before add_app when the user gives an app name. Returns at most 12 apps, in Apple's name-search order, which is not the keyword ranking: for who ranks for a keyword, use get_keyword_top_apps. Screenshot
add_keywordsAdd one or more tracked keywords to an app in the current Asonix workspace and queue ranking refresh so popularity, difficulty, opportunity, and rank evidence can be collected. For agent-researched candidates, call evaluate_keywords first and add app-relevant primary or secondary
star_keywordStar/favorite a keyword research keyword in the current workspace by keywordId or term.
unstar_keywordRemove a keyword research keyword from the current workspace favorites by keywordId or term.
list_appsList apps tracked in the current Asonix workspace: names, App Store IDs, platforms, tracked storefronts, ratings and tracked-keyword counts. Pages with limit (default 20, max 100) and offset; q filters by name, developer, genre or ID. For one app's details use get_app_overview; f
list_tracked_keywordsOne tracked app's tracked keywords with rank, popularity, difficulty, relevance and an ad summary, in one storefront or all. Use it for "how are my keywords doing". For the app's listing or ratings, or an untracked app, use get_app_overview. Paged: limit (default 30, max 100) and
get_app_meta_adsAn App Store app's Meta ads (Facebook, Instagram, Messenger, Audience Network) from Asonix's monthly Ad Library crawl, worldwide, for any app: active ads with text, call to action, start date, platforms and an Ad Library link, and past ads with their dates. status not_found is no
refresh_app_rankingsQueue a ranking refresh for one tracked app's keywords not checked in the last 18 hours, and return at once with jobIds. Omit country for every tracked storefront; one refreshed recently is listed in coolingDown. A refresh can take 10 minutes or more, so do not wait in a loop: te
get_ranking_refresh_statusReport progress of a ranking refresh started by refresh_app_rankings, or of the rankingRefreshJob id returned by add_keywords: keywords done, failed, and remaining per storefront. Poll no more often than pollAfterSeconds. When finished is true, read the full updated ranks with li
get_workspace_keyword_opportunitiesReturn top scored keyword opportunities across all tracked apps in the current Asonix workspace, including shipped and unreleased apps, all countries, and rank/popularity/difficulty/opportunity evidence. Use this for requests like analyzing all apps or finding the top 100 opportu
check_tracked_keywordsCheck candidate keyword terms against one tracked app's existing tracked keywords without dumping the full keyword table. iOS keyword rows include cached topAdvertisers; pending observations queue in the background. Use this before calling a candidate a missing gap, before add_ke
get_app_overviewAn app's overview in one storefront, for any App Store app. storeListing is the storefront's listing and rating. Lists are counts: include adds the full description, countryRatings, listingCountries or keywordSuggestions. tracked says whether the workspace tracks it; its keywords
get_app_visibility_historyReturn tracked ASO visibility score history for an app, useful for momentum and trend analysis.
get_app_rank_historyReturn rank, popularity, or difficulty history for one tracked app keyword in a storefront.
get_app_rating_historyReturn stored public rating history for any App Store app, tracked or not, with deltas: the history the Inspect dialog shows. Asonix records rating history only while some workspace tracks the app, so an app no workspace has tracked has none; for current ratings of any app, use g
get_app_chartsWhere any App Store app placed in Apple's iPhone top charts (free, paid, grossing; overall and by category) per storefront: best rank, days on chart, latest position. days: 7, 30 (default), 90 or 365. includeDailyCells adds a cell per chart per day: a number is the best position,
get_keyword_suggestions_for_appRefresh and return Asonix keyword suggestions for one tracked app and storefront. Includes suggestionRelevance rows and inline metadata-plan relevanceScore/relevanceStatus; missing scores queue in the background.
research_app_keywordsStart keyword research for a tracked app in one call: Asonix suggestions, known public rankings and market keyword opportunities, each with the app's relevance. It can refresh the suggestion list, which spends the app's daily budget. Seed searches are checked privately unless sto
extract_competitor_keywordsExtract keyword opportunities from competitor public rankings and compare them against the tracked app. Includes relevanceScore/relevanceStatus for the target app, not the competitors; missing scores queue in the background. Provide competitorAppStoreIds, or provide a seed keywor
get_localization_opportunitiesBuild and return localization and translated market keyword opportunity requests for one tracked app.
get_public_app_rankingsReturn known public App Store keyword rankings where an app appears in collected SERPs.
search_keywordsSearch Asonix keyword research summaries by query, market, platform, scores, and market estimates. iOS keyword rows include cached topAdvertisers; pending observations queue in the background, so retry this tool later.
get_keyword_relevanceApp-specific relevance (0–100) of up to 100 keywords for a tracked app, from the same scorer as the UI. Returns at once with ready, pending, failed or unavailable for each keyword. Pending is not zero: call again after 3 seconds or more, backing off. retry=true retries failed wor
evaluate_keywordsRank and classify candidate keywords by Asonix popularity, difficulty and opportunity. Use it before recommending keywords or calling add_keywords. Known keywords reuse stored scores; up to 20 new ones per call are scored privately, without adding them to public research. Pass po
get_keyword_top_appsWho ranks for a keyword in one storefront; appStoreId gives that app's rank. Uses results Asonix checked in the last 18 hours, else a private live check; saves nothing. Adds stored scores when Asonix has them; to score a new keyword, use evaluate_keywords. To find an app by name,
get_keyword_top_advertisersApps seen in native App Store search ads for one iPhone keyword in one Apple Ads country: the last 7 days' check coverage, last seen, and 30 days of history. Cached only, no live Apple request; pending collection fills in on a later call. Absence does not prove an app stopped bid
get_app_search_ads_keywordsKeywords where an iPhone app's App Store search ads were seen in the last 30 days, in all countries or one. Asonix checks each keyword about once a day, so a missing keyword may still be bid on. observedSharePercent7d is the share of the last 7 days' checks that showed the ad, no
get_keyword_historyReturn keyword popularity or difficulty history for an Asonix keyword, with cached topAdvertisers for eligible iOS keywords. Pending advertiser observations are queued; retry later.
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月6日にチェック
レジストリにソースのリポジトリが載っていないため、公開者(asonix.io)とコードを照合できません
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
142ミリ秒で応答(HTTP 200)
サインイン不要
33件のツールの説明を読み、AIへの隠れた指示は見つかりませんでした
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック3項目のうち2項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:Authorization
作者のクラウドで動きます。インストール不要でインターネット経由でつながりますが、送った内容は作者のサーバーを通ります。
GitHubリポジトリの最終更新は–、最新バージョン(1.0.0)がレジストリに届いたのは一昨日です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。URLでつながるので、リモートMCPサーバーに対応したアプリ(開発者モードのChatGPTなど)でも使えます。
同じカテゴリには:MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
リポジトリにREADMEが見つかりません