# App Review Teardown & Insights (AI) (`scrapebench/reviews-insight-mcp`) Actor Turn any app's App Store + Google Play reviews into an AI competitive teardown — strengths, weaknesses, top complaints, feature requests — and track what changes over time. - **URL**: https://apify.com/scrapebench/reviews-insight-mcp.md - **Developed by:** [ScrapeBench](https://apify.com/scrapebench) (community) - **Categories:** AI - **Stats:** 3 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing $0.05 / ai-insight This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## App Review Teardown & Insights (AI) ### Pain points - Reading hundreds of app reviews to understand a competitor's strengths and weaknesses takes hours. - Spotting the top complaints and feature requests across a category means manual slogging. - Catching when a rival's rating slips or new complaints emerge requires constant re-checking. ### What we solve - Turn any app's App Store + Google Play reviews into an AI teardown: strengths, weaknesses, top complaints, feature requests, themed sentiment. - Drop in several apps for a side-by-side competitive battlecard. - Run on a schedule to track what changed — rating moves, emerging vs resolved complaints, sentiment shifts. - Also callable as an MCP tool by AI agents. ### Summary Point it at any app — by name, store URL, or id — and get back an AI **competitive teardown** of its App Store (and Google Play) reviews: a summary, strengths, weaknesses, top complaints, requested features, and themed sentiment. Drop in several apps to tear down competitors side by side. Run it on a schedule and it also reports **what changed** since last time — rating moves, emerging vs resolved complaints, sentiment shifts — turning competitor and product monitoring into a set-and-forget task. Also callable as an MCP tool by AI agents. ### Who it's for - Product managers prioritizing from user feedback - GTM and sales teams building competitive battlecards - Competitive-intelligence and market researchers - AI agents needing review insight as an MCP tool ### How to use Set the input, run the actor, and collect results from the run's dataset (export to JSON/CSV/Excel, or pull via the Apify API). Example input: ```json { "apps": [ "Notion", "Evernote" ], "yourApp": "Notion", "maxReviews": 100, "compareToPrevious": true } ```` See **Inputs** below for every available field. ### What you get One row per record: | Field | Description | |---|---| | `app` | The app reference you supplied | | `app_name` | Resolved app name | | `sources` | Stores that contributed reviews (apple, gplay) | | `overall_rating` | Store-reported average rating | | `review_count_analyzed` | Reviews fed to the AI | | `teardown.summary` | One-paragraph competitive summary | | `teardown.strengths / weaknesses` | What users love / dislike | | `teardown.top_complaints` | The most common complaints | | `teardown.feature_requests` | Features users ask for | | `teardown.themes` | Recurring themes with sentiment + mention counts | | `teardown.sentiment_score` | Overall sentiment 0–100 | | `emerging_complaints / resolved_complaints` | Complaints that appeared / disappeared since last run (monitoring) | | `rating_delta / sentiment_delta` | Changes since the previous run | | `comparison` | When 2+ apps: an extra record with a strengths/weaknesses matrix + sales battlecards (their weaknesses, where you win, watch-outs) | | `source_url` | The app's store page | Sample: ```json { "app": "Notion", "app_name": "Notion: Notes, Tasks, AI", "apple_id": "1232780281", "sources": [ "apple" ], "overall_rating": 4.78, "review_count_analyzed": 100, "teardown": { "summary": "Notion is praised as a powerful, flexible workspace but is dragged down by mobile bugs, a steep learning curve, and an intrusive AI button.", "strengths": [ "Powerful, flexible all-in-one workspace", "Great for notes, tasks, and databases" ], "weaknesses": [ "Buggy on iOS/iPad with crashes", "Steep learning curve on mobile", "Intrusive AI chat button" ], "top_complaints": [ "app crashes / bugs", "confusing mobile navigation", "free-tier upload limits" ], "feature_requests": [ "offline mode", "remove/hide the AI button", "better mobile editor" ], "themes": [ { "theme": "Bugs and crashes", "sentiment": "negative", "mentions": 6 }, { "theme": "Power and flexibility", "sentiment": "positive", "mentions": 5 } ], "sentiment_score": 62 }, "first_seen": false, "rating_delta": -0.03, "emerging_complaints": [ "app crashes / bugs" ], "resolved_complaints": [], "sentiment_delta": -4, "source_url": "https://apps.apple.com/us/app/id1232780281" } ``` ### Inputs | Field | Required | Type | Default | Description | |---|---|---|---|---| | `apps` | yes | array | `["Notion"]` | Apps to analyze — an app name (e.g. 'Notion'), an App Store / Google Play URL, an Apple numeric id, or a Google Play package (com.x.y). One competitive teardown per app. Provide several to teardown competitors side by side. | | `maxReviews` | no | integer | `100` | Reviews sampled per app (most-recent first) and fed to the AI. Caps cost; more reviews = richer teardown. | | `country` | no | string | `"us"` | Two-letter store country code for reviews (e.g. 'us', 'gb', 'de'). | | `compareApps` | no | boolean | `true` | When 2+ apps are given (default on), add a cross-app comparison record — a strengths/weaknesses matrix plus sales battlecards (their weaknesses, where you win, what to watch out for). | | `yourApp` | no | string | — | Optional. Name one of the apps as yours, and battlecards are framed as YOUR app vs each competitor. Leave empty for a neutral comparison. | | `compareToPrevious` | no | boolean | `true` | When on (default), diff each app against the previous run and report what changed — rating delta, emerging vs resolved complaints, sentiment delta. Run on a schedule to track competitors over time. | | `proxyConfiguration` | no | object | `{"useApifyProxy": false}` | Optional. The app-store endpoints are reachable directly; a proxy is rarely needed. | ### Pricing (Pay Per Event) You pay per result (`ai-insight`) — **no charge for empty runs**. Example: **20 app teardowns** at *$0.05/result* ≈ **$1.00**. One charge per app teardown produced. Apps we can't find / with no reviews are not charged. Apify platform usage (compute) is billed separately per your plan. ### Use cases - Competitor teardown — PMs and GTM teams see a rival app's strengths, weaknesses, and top complaints. - Sales battlecards — drop in your app plus competitors and get a side-by-side comparison. - Product prioritization — surface the most-requested features and biggest complaints from your own reviews. - Monitoring — run weekly to catch rating drops and emerging complaints on competitor apps. ### Why this actor - An AI teardown, not raw reviews — strengths, weaknesses, complaints, and feature requests. - Compare multiple apps side-by-side and track how sentiment changes over time. - Callable as an MCP tool, so AI agents can pull review insight directly. ### Limitations & updates Analyzes public app-store reviews only (Apple App Store via the official iTunes feed; Google Play best-effort). The AI teardown is generated from the most-recent sampled reviews (capped by maxReviews) and reflects what reviewers wrote — not internal metrics. Apps with no reviews or that can't be resolved are returned empty and not charged. ### FAQ **What does it analyze?** App Store and Google Play reviews for the apps you specify, turned into an AI competitive teardown. **What's in the output?** A summary plus strengths, weaknesses, top complaints, requested features, and themed sentiment — per app. **Can I compare competitors?** Yes — pass several apps and get a side-by-side battlecard of where each wins and what users complain about. **Can AI agents call it?** Yes — it's exposed as an MCP tool, so agents can pull review insight directly into their workflow. **How am I charged?** Per app teardown (an AI-insight event) — you're billed for the analysis produced. **Can it track changes?** Yes — run on a schedule and it reports rating moves and emerging vs. resolved complaints over time. ### Guides & use cases Written up on **[scrapebench.dev](https://scrapebench.dev)** — the bench that runs and verifies this actor against the live source every night: - **How-to:** [How to run App Review Teardown & Insights (AI)](https://scrapebench.dev/guides/how-to-reviews-insight-mcp/) - **Use case:** [AI Teardown of an App's App Store Reviews](https://scrapebench.dev/use-cases/ai-teardown-of-app-store-reviews/) - **Use case:** [Compare Two Competitor Apps' Reviews](https://scrapebench.dev/use-cases/compare-two-competitor-apps-reviews/) - **Use case:** [Find the Top Complaints in an App's Reviews](https://scrapebench.dev/use-cases/find-top-complaints-in-app-reviews/) More actors, coverage and nightly verification results: **[scrapebench.dev](https://scrapebench.dev)** # Actor input Schema ## `apps` (type: `array`): Apps to analyze — an app name (e.g. 'Notion'), an App Store / Google Play URL, an Apple numeric id, or a Google Play package (com.x.y). One competitive teardown per app. Provide several to teardown competitors side by side. ## `maxReviews` (type: `integer`): Reviews sampled per app (most-recent first) and fed to the AI. Caps cost; more reviews = richer teardown. ## `country` (type: `string`): Two-letter store country code for reviews (e.g. 'us', 'gb', 'de'). ## `compareApps` (type: `boolean`): When 2+ apps are given (default on), add a cross-app comparison record — a strengths/weaknesses matrix plus sales battlecards (their weaknesses, where you win, what to watch out for). ## `yourApp` (type: `string`): Optional. Name one of the apps as yours, and battlecards are framed as YOUR app vs each competitor. Leave empty for a neutral comparison. ## `compareToPrevious` (type: `boolean`): When on (default), diff each app against the previous run and report what changed — rating delta, emerging vs resolved complaints, sentiment delta. Run on a schedule to track competitors over time. ## `proxyConfiguration` (type: `object`): Optional. The app-store endpoints are reachable directly; a proxy is rarely needed. ## Actor input object example ```json { "apps": [ "Notion", "com.evernote" ], "maxReviews": 100, "country": "us", "compareApps": true, "compareToPrevious": true, "proxyConfiguration": { "useApifyProxy": false } } ``` # Actor output Schema ## `teardowns` (type: `string`): Per-app competitive teardown (strengths, weaknesses, complaints, feature requests, themes) + what changed since last run. # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "apps": [ "Notion" ] }; // Run the Actor and wait for it to finish const run = await client.actor("scrapebench/reviews-insight-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "apps": ["Notion"] } # Run the Actor and wait for it to finish run = client.actor("scrapebench/reviews-insight-mcp").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "apps": [ "Notion" ] }' | apify call scrapebench/reviews-insight-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=scrapebench/reviews-insight-mcp", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "App Review Teardown & Insights (AI)", "description": "Turn any app's App Store + Google Play reviews into an AI competitive teardown — strengths, weaknesses, top complaints, feature requests — and track what changes over time.", "version": "0.1", "x-build-id": "YwBc7rVCLQV4V73je" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapebench~reviews-insight-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapebench-reviews-insight-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapebench~reviews-insight-mcp/runs": { "post": { "operationId": "runs-sync-scrapebench-reviews-insight-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapebench~reviews-insight-mcp/run-sync": { "post": { "operationId": "run-sync-scrapebench-reviews-insight-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "apps" ], "properties": { "apps": { "title": "Apps", "type": "array", "description": "Apps to analyze — an app name (e.g. 'Notion'), an App Store / Google Play URL, an Apple numeric id, or a Google Play package (com.x.y). One competitive teardown per app. Provide several to teardown competitors side by side.", "items": { "type": "string" } }, "maxReviews": { "title": "Max reviews per app", "minimum": 10, "maximum": 500, "type": "integer", "description": "Reviews sampled per app (most-recent first) and fed to the AI. Caps cost; more reviews = richer teardown.", "default": 100 }, "country": { "title": "Store country", "type": "string", "description": "Two-letter store country code for reviews (e.g. 'us', 'gb', 'de').", "default": "us" }, "compareApps": { "title": "Compare apps (battlecards)", "type": "boolean", "description": "When 2+ apps are given (default on), add a cross-app comparison record — a strengths/weaknesses matrix plus sales battlecards (their weaknesses, where you win, what to watch out for).", "default": true }, "yourApp": { "title": "Your app (battlecard perspective)", "type": "string", "description": "Optional. Name one of the apps as yours, and battlecards are framed as YOUR app vs each competitor. Leave empty for a neutral comparison." }, "compareToPrevious": { "title": "Monitor changes", "type": "boolean", "description": "When on (default), diff each app against the previous run and report what changed — rating delta, emerging vs resolved complaints, sentiment delta. Run on a schedule to track competitors over time.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. The app-store endpoints are reachable directly; a proxy is rarely needed.", "default": { "useApifyProxy": false } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```