MCP tools

AI Visibility Overview

Read 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. Use list_apps to resolve the app and storefront.

AI Recommendation Reasons

Read 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 matched passages and description metadata. Use theme and evidenceLimit to drill into supporting quotes.

AI Visibility Evidence

Read 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 sources belong to a search call, not an individual query. No external requests or collection.

Give exactly one of: runId, promptId.

Add App

Add an App Store app to the current Asonix workspace by App Store ID or app name/search query.

Create Unreleased App

Create 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 Apps

Search the public App Store by app name/query and return app IDs, names, categories, developers, ratings, URLs, and screenshot URLs. Use before add_app when the user gives an app name.

Search Live App Store

Search the live App Store ranking for a keyword to validate search intent and inspect competitors. Returns up to 100 ranked apps with enriched subtitles for the most important results. Screenshot URLs are opt-in and limited to the first 10 apps. This is private, read-only, and does not calculate popularity or difficulty; use evaluate_keywords for scores. Each app includes runsAppleSearchAds. runsAppleSearchAds is yes when the app appeared in a sampled iPhone App Store search ad in that country within seven days. unknown is not proof the app is not bidding: no sampled ad showed it, or Asonix does not sample that storefront. unavailable means the status read failed.

Add Keywords

Add 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 terms.

Star Keyword

Star/favorite a keyword research keyword in the current workspace by keywordId or term.

Unstar Keyword

Remove a keyword research keyword from the current workspace favorites by keywordId or term.

List Apps

List apps tracked in the current Asonix workspace, including names, App Store IDs, platforms, countries, ratings, and tracked-keyword counts.

Get Tracked App

Return one tracked Asonix workspace app with its listing screenshots, tracked keywords, and current ranking context. Includes app-specific relevanceScore and relevanceStatus on each tracked keyword; missing scores queue in the background. app.runsAppleSearchAds applies to app.runsAppleSearchAdsCountry: the requested country, else the app's home country. runsAppleSearchAds is yes when the app appeared in a sampled iPhone App Store search ad in that country within seven days. unknown is not proof the app is not bidding: no sampled ad showed it, or Asonix does not sample that storefront. unavailable means the status read failed. Each rank has checkedAt; the result flags ranks more than 18 hours old or never checked, and refresh_app_rankings updates them.

App Meta Ads

Return an App Store app's Meta (Facebook, Instagram, Messenger, Audience Network) ads from Asonix's shared Meta Ad Library catalog, worldwide: active ads that link to the app in the App Store, with text, call to action, start date, platforms and an Ad Library link, and past ads with the dates they ran. Works for any app, tracked or not. An app with no ads in the catalog returns status not_found, which is not proof it never ran Meta ads: the catalog covers App Store ads found by a monthly crawl.

Refresh App Rankings

Queue a keyword ranking refresh for one tracked app and return at once with jobIds. Only keywords not checked in the last 18 hours are queued; keywords already refreshing are joined, not queued twice. A storefront whose refresh was requested recently is skipped and listed in coolingDown with the time it can start again. Omit country to refresh every tracked storefront of the app. A refresh can take 10 minutes or more, so do not wait in a loop: tell the user rankings are updating, then call get_ranking_refresh_status with the jobIds after pollAfterSeconds, or read get_app later.

Ranking Refresh Status

Report 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 get_app.

Workspace Keyword Opportunities

Return 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 opportunities without reading a local database. Each opportunity has checkedAt; call refresh_app_rankings for an app whose ranks are old.

Check Tracked Keywords

Check 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_keywords, and instead of inspecting local database code.

App Overview

Return one tracked app's listing metadata, countries, ratings context, and compact Asonix app summary. app.runsAppleSearchAds applies to app.runsAppleSearchAdsCountry: the requested country, else the app's home country. runsAppleSearchAds is yes when the app appeared in a sampled iPhone App Store search ad in that country within seven days. unknown is not proof the app is not bidding: no sampled ad showed it, or Asonix does not sample that storefront. unavailable means the status read failed.

App Visibility History

Return tracked ASO visibility score history for an app, useful for momentum and trend analysis.

App Rank History

Return rank, popularity, or difficulty history for one tracked app keyword in a storefront.

App Rating History

Return stored public rating history for one tracked app with deltas. Omit country or pass "all" to return every observed storefront plus the all-countries aggregate; pass a country code to return only that storefront.

App Keyword Suggestions

Refresh 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 Keywords

Start ASO keyword research for a tracked app in one call: app context, Asonix suggestions, known public rankings, and market keyword opportunities, each with target-app relevanceScore and relevanceStatus. Suggested strings have parallel suggestionRelevance rows. iOS keyword rows include cached topAdvertisers; pending observations queue in the background, so retry this tool later. Missing relevance scores also queue. Raw seed SERPs are checked privately unless storePublicly is true. Before final recommendations or add_keywords, rank and classify candidate terms with evaluate_keywords.

Competitor Keywords

Extract 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 keyword to discover competitors from a private live SERP unless storePublicly is true. Rank and classify candidates with evaluate_keywords before recommending or adding them.

Localization Opportunities

Build and return localization and translated market keyword opportunity requests for one tracked app.

Public App Rankings

Return known public App Store keyword rankings where an app appears in collected SERPs.

Search Keywords

Search 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.

Keyword Relevance

Get app-specific keyword relevance (0–100) for a tracked workspace app using the same revised-selective scorer as the UI. Accepts up to 100 keywords. Reuses cached scores and queues missing work; returns immediately with ready, pending, failed or unavailable statuses. Pending is not zero: call again after at least three seconds, backing off on repeated pending responses. Use retry=true only to retry failed work after its cooldown. Does not add keywords to tracking or public research. Country defaults to us and platform to ios.

Evaluate Keywords

Rank and classify candidate ASO keywords against Asonix popularity, difficulty, and opportunity stats. If a candidate includes popularityScore and difficultyScore, evaluate those values directly. Otherwise, reuse an existing public keyword row when available; missing candidate terms are scored privately with the same Asonix SERP scoring model without adding them to public keyword research. Up to 20 new/private terms are scored per call; split larger unknown batches or pass known scores. Use this before final keyword recommendations, add_keywords, or star_keyword. Supply appStoreId for inline relevanceScore and relevanceStatus. Missing scores queue in the background; use get_keyword_relevance to check pending scores. Decisions and ranking still reflect market metrics; assess app fit separately using relevance.

Keyword Top Apps

Return top ranking App Store apps for an Asonix keywordId or a live App Store keyword/term, with cached topAdvertisers for eligible iOS keywords. Pending advertiser observations are queued; retry later. Raw keyword/term lookups are checked privately unless storePublicly is true. Each app includes runsAppleSearchAds. runsAppleSearchAds is yes when the app appeared in a sampled iPhone App Store search ad in that country within seven days. unknown is not proof the app is not bidding: no sampled ad showed it, or Asonix does not sample that storefront. unavailable means the status read failed.

Keyword Top Advertisers

Return cached apps observed in native App Store search ads for one authorized iPhone keyword/storefront. Shows seven-day successful-check coverage, last seen, and 30-day history. Pending collection is queued; call again later. No live Apple request is made by this tool. Absence does not prove bidding stopped or an app was outbid. Requires an explicit Apple Ads search-results country and exactly one of keywordId or term.

Keyword History

Return keyword popularity or difficulty history for an Asonix keyword, with cached topAdvertisers for eligible iOS keywords. Pending advertiser observations are queued; retry later.

Check Keyword Search Results

Check a live App Store keyword SERP privately by default. Includes cached topAdvertisers for eligible iOS keywords; pending advertiser observations are queued, so retry later. Set storePublicly to true only when the user wants to add/reuse the keyword in the shared public research index. Each topApps row includes runsAppleSearchAds. runsAppleSearchAds is yes when the app appeared in a sampled iPhone App Store search ad in that country within seven days. unknown is not proof the app is not bidding: no sampled ad showed it, or Asonix does not sample that storefront. unavailable means the status read failed.