MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
제작자가 쓴 설명(영어 원문)
ASO for your AI: keywords, rankings, competitors and ads across 2.5M+ App Store apps.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
Authorization필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
이 주소는 요청 header에 키가 필요한데, 커넥터 추가 메뉴에서는 넣을 수 없어요. 대신 Claude Code, Cursor, VS Code를 쓰세요.
터미널에서 이 명령어를 실행하세요
claude mcp add --transport http asonix https://api.asonix.io/mcp --header 'Authorization: Bearer {token}'실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"asonix": {
"url": "https://api.asonix.io/mcp",
"headers": {
"Authorization": "Bearer {token}"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"asonix": {
"type": "http",
"url": "https://api.asonix.io/mcp",
"headers": {
"Authorization": "Bearer {token}"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 주소는 요청 header에 키가 필요한데, 커넥터 추가 메뉴에서는 넣을 수 없어요. 대신 Claude Code, Cursor, VS Code를 쓰세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
Authorization 필수 HTTP header이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
도구 이름과 설명은 서버가 2026년 11월 6일에 알려 준 그대로예요. 우리가 아니라 제작자가 쓴 글이고, 일반 텍스트로만 보여 드려요.
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.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
레지스트리에 소스 저장소가 없어서, 게시자(asonix.io)와 코드를 맞춰 볼 수 없어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
142ms 만에 응답(HTTP 200)
로그인 필요 없음
도구 설명 33개를 읽었고, AI에게 보내는 숨겨진 지시는 없었어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 3개 중 2개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
입력해야 할 값: Authorization
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.0.0)은 그저께 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
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.
저장소에서 README를 찾지 못했어요