App Store Operator

Fetch SensorTower analytics for one or more App Store app IDs. Returns downloads, revenue, ratings, publisher info, markets, and more for each app. Use this when you already have app IDs (e.g. from `search_app_store`) and want detailed analytics for only a subset of them — avoiding unnecessary scrapes for apps you don't need. Use `research_rivals` instead for a single convenience call that searches and fetches analytics together. Do not use this for Google Play or Android apps — it takes numeric iOS App Store IDs only. Requires a SensorTower account. The server opens a real Chromium window on the user's machine; the first run needs the user to log in there, and the session is reused from then on. If there is no session the call returns an error result carrying `{"error": "not_logged_in"}` and leaves the window open — tell the user to log in, then call again. Results are never cached, so every call scrapes fresh and costs roughly 10–20 seconds per app ID. Returns JSON: ```json { "country": "us", "fetchedAt": "2026-04-21T10:00:00.000Z", "apps": [ { "rank": 1, "name": "App Name", "appStoreUrl": "...", "sensorTowerUrl": "...", "downloads": "<5K", "revenue": "<$5K", "rating": { "score": "4.7", "count": "1,234" }, "publisher": "Publisher Name", "categories": "Health & Fitness", "topMarkets": "United States, United Kingdom", "releaseDate": "Jan 1, 2020", "lastUpdated": "Mar 15, 2026", "languages": "English, Spanish", "inAppPurchases": "Monthly · $9.99", "publisherCountry": "United States", "advertisingNetworks": "N/A" } ] } ``` Fields missing or gated behind a paywall will be `"N/A"`. A single app failing to scrape is not fatal — that app comes back with `"N/A"` fields rather than failing the whole call.

Prepare an iOS App Store In-App Event (IAE) — generate copy variations and a final report. Use this when the user wants to create or draft an in-app event, prepare IAE metadata, or generate App Store event copy. Accepts user-supplied keywords and event parameters, then returns a structured brief. Do not use it for ordinary App Store listing metadata (title, subtitle, description) — it covers In-App Event fields only. Runs entirely locally: no network calls, no App Store or SensorTower lookup, and no keyword research of its own — the caller supplies the keywords (reach for `research_rivals` or `search_app_store` first if you still need to find them). Returns immediately. **After receiving the tool output, you MUST:** 1. Generate **3 distinct copy variations** in the target language (from `locale.language`), each differing meaningfully in angle, tone, or keyword emphasis. For each variation produce: - **Event name** (hard limit: 30 chars — count every character; trim at word boundary if over) - **Short description** (hard limit: 50 chars — same rules) - **Long description** (hard limit: 120 chars — same rules) Display every field with its exact character count and ✓ / ✗ indicator. Fix any ✗ before showing the user. Keyword placement: Tier 1 keywords must appear in short description and long description; embed in event name only if it fits naturally. Prioritize keywords toward the beginning of each field. Copy rules: active voice, present tense, no pricing claims or % discounts, no competitor names, all three fields independently meaningful. If locale is not en-US, add an English translation line under each localized field so the user can verify meaning. 2. Ask the user to choose one variation. 3. After the user picks a variation, print the **output table** and the **final summary report** using this exact format: **Output table:** ``` CHOSEN VARIATION — <locale.appleCode> ───────────────────────────────────── Event name : <text> (<N>…

Search the App Store for a keyword and fetch SensorTower analytics for the top results — all in one call. Results are cached for 24 hours so repeat queries are instant. Use this for a quick competitive overview when you want everything in one step. Use `search_app_store` + `get_app_details` separately when you need more than 3 results, a custom limit, or selective fetching of specific apps. Do not use this for Google Play or Android apps — it covers the iOS App Store only. Requires a SensorTower account. On a cache miss the server opens a real Chromium window on the user's machine; the first run needs the user to log in there, and the session is reused from then on. If there is no session the call returns an error result carrying `{"error": "not_logged_in"}` and leaves the window open — tell the user to log in, then call again. A cache miss scrapes three apps and typically takes 30–60 seconds; a cache hit returns immediately and opens no browser. Trigger phrases: "rival research", "research rivals", "competitor analysis", "find competing apps", "check competitors", "what apps compete with", "App Store competitors", "rivals for keyword". Returns JSON: ```json { "keyword": "meditation", "country": "us", "fetchedAt": "2026-04-21T10:00:00.000Z", "cached": false, "apps": [ { "rank": 1, "name": "App Name", "appStoreUrl": "https://apps.apple.com/us/app/id123456", "sensorTowerUrl": "https://app.sensortower.com/overview/123456", "downloads": "<5K", "revenue": "<$5K", "rating": { "score": "4.7", "count": "1,234" }, "publisher": "Publisher Name", "categories": "Health & Fitness", "topMarkets": "United States, United Kingdom", "releaseDate": "Jan 1, 2020", "lastUpdated": "Mar 15, 2026", "languages": "English, Spanish", "inAppPurchases": "Monthly · $9.99", "publisherCountry": "United States", "advertisingNetworks": "N/A" } ] } ``` Fields missing or gated behi…

Search the App Store for a keyword and return ranked results as a detailed table — instantly, no browser required. Use this when you want to discover which apps rank for a keyword before deciding which ones to analyse in depth. - Follow up with `get_app_details` to fetch SensorTower analytics for specific app IDs. - Use `research_rivals` instead for a single convenience call that searches and fetches analytics together. - Do not use this for Google Play or Android apps — it covers the iOS App Store only. Unlike `research_rivals` and `get_app_details`, this needs no SensorTower account, opens no browser window, and returns in about a second. It also carries no downloads or revenue figures — those only come from the SensorTower tools. Returns markdown (not JSON): one table per result, ranked, with every App Store field available including the numeric app ID that `get_app_details` takes. Unavailable fields read `"N/A"`. A keyword with no matches returns just the header line and no tables.