App Store & Google Play Reviews MCP Server

Give your AI agent live access to the Apple App Store and Google Play: search apps, read store listings, pull user reviews, and get a ready-made review insights report (top complaints, top praise, rating by app version and month) — or compare up to 5 competitor apps in one call. Works with Claude Desktop, Claude Code, Cursor, VS Code, n8n, LangChain and any other MCP client.

Tools

Tool	What it does	Price
search_apps	Keyword search on App Store, Google Play or both. Returns ids, names, developers, ratings, price, URLs.	$0.005 / call
get_app_details	Full listing: rating, rating count, star histogram, installs, price, in-app purchases, version, last update, release notes, description.	$0.005 / call
get_app_reviews	Recent or most helpful reviews with rating, title, text, version, date, helpful votes and developer reply. Filter by star rating. Up to 500 per call.	$0.005 per 50 reviews
analyze_app_reviews	Insights report from up to 500 latest reviews: average rating, distribution, negative share, top complaint and praise topics, rating by version and month, developer reply rate, short quotes.	$0.03 / app
compare_apps	Side-by-side insights for 2–5 apps (mix of iOS and Android allowed).	$0.03 / app

Apps can be given as a store URL, an Apple numeric id (1232780281), an Android package name (com.whatsapp), or a plain name (then pass store). 150+ countries via country (us, gb, de, my, …).

Why this server

• Answers, not raw dumps. analyze_app_reviews returns a compact summary your agent can reason about instead of thousands of review rows that fill its context window.
• Both stores in one server. No need to wire two scrapers together.
• Compact output. Review text is truncated (configurable), JSON is minified — fewer tokens per call.
• You only pay for results. Failed calls, "app not found" and errors are never charged.

Example prompts

• "What do users complain about most in Duolingo's latest Android reviews?"
• "Compare Todoist, TickTick and Things 3 reviews — where is each one weak?"
• "Find the top 10 habit tracker apps on the US App Store and show their ratings."
• "Show me 1- and 2-star Notion reviews from the UK App Store since the last update."

Connect

MCP endpoint (Streamable HTTP):

https://rasareka--app-reviews-mcp.apify.actor/mcp

Authenticate with your Apify API token (Console → Settings → API & Integrations) as a Bearer header.

Claude Desktop / Cursor / VS Code (mcp.json / claude_desktop_config.json):

{
  "mcpServers": {
    "app-reviews": {
      "url": "https://rasareka--app-reviews-mcp.apify.actor/mcp",
      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}

For clients that only support stdio:

{
  "mcpServers": {
    "app-reviews": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://rasareka--app-reviews-mcp.apify.actor/mcp", "--header", "Authorization: Bearer YOUR_APIFY_TOKEN"]
    }
  }
}

Claude Code:

$claude mcp add --transport http app-reviews https://rasareka--app-reviews-mcp.apify.actor/mcp --header "Authorization: Bearer YOUR_APIFY_TOKEN"

You can also reach it through the Apify MCP server at mcp.apify.com by adding the Actor rasareka/app-reviews-mcp.

Example output

analyze_app_reviews for com.todoist (100 latest US reviews, shortened):

{
  "app": { "store": "google", "appId": "com.todoist", "name": "Todoist: To Do List & Calendar", "rating": 4.61, "ratingCount": 307498, "installs": "10,000,000+" },
  "reviewsAnalyzed": 100,
  "averageRating": 3.93,
  "ratingDistribution": { "1": 14, "2": 7, "3": 9, "4": 12, "5": 58 },
  "negativeShare": 0.21,
  "developerReplyRate": 0.85,
  "topComplaints": [
    { "term": "task", "mentions": 5, "shareOfReviews": 0.238 },
    { "term": "add", "mentions": 4, "shareOfReviews": 0.19 },
    { "term": "feature", "mentions": 3, "shareOfReviews": 0.143 }
  ],
  "ratingByVersion": [{ "version": "v12296", "reviews": 8, "averageRating": 4.5 }],
  "sampleNegativeQuotes": [{ "rating": 1, "date": "2026-11-08", "text": "A review should be freely given, not coerced. When an app interrupts my experience to demand a rating…" }]
}

Pricing

Pay per event — you pay only for successful tool calls (see the table above). A typical "analyze 3 competitors" session costs about $0.10. Set a spending limit in Apify and the server stops charging when it is reached. Apify's free plan includes monthly credit, enough to try every tool.

Limits (honest)

• Apple publishes at most 500 reviews per app per country in its public feed, newest or most helpful only.
• Google Play reviews come in the store's language/country you set; very old reviews may not be reachable.
• Topic extraction is keyword-based (no LLM inside), so your agent should read the quotes for nuance.
• Data is fetched live from public store pages; if a store changes its format a tool may fail until updated (you are not charged for failures).

FAQ

Do I need an App Store / Google developer account? No. Only an Apify account (free).

Is it legal? The server reads publicly available store listings and reviews only — no login, no private data. You are responsible for how you use the data and for complying with the stores' terms and laws such as GDPR. Reviewer names are public store usernames.

Does a normal run do anything? A normal (non-Standby) run does a quick self-test and exits. Use the Standby URL above for MCP.

Need another tool? Open an issue on the Actor page.