# App Store & Google Play Reviews MCP Server (`rasareka/app-reviews-mcp`) Actor

MCP server for AI agents: search App Store and Google Play apps, get app details, fetch user reviews and get review insights (top complaints, praise, rating by version) or compare competitor apps. Works with Claude, Cursor, n8n and any MCP client.

- **URL**: https://apify.com/rasareka/app-reviews-mcp.md
- **Developed by:** [Rasa Reka](https://apify.com/rasareka) (community)
- **Features:** Limited permissions, Single-tenant, Server interface
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $5.00 / 1,000 search or app details

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
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.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## 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`):

```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:

```json
{
  "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:**

```bash
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):

```json
{
  "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.

# Actor input Schema

## Actor input object example

```json
{}
```

# Actor output Schema

## `results` (type: `string`):

No description

# 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 '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("rasareka/app-reviews-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 '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("rasareka/app-reviews-mcp").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call rasareka/app-reviews-mcp --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,rasareka/app-reviews-mcp"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/XuH3yqjV41QgyuDjh/builds/K8ARYJT2RRTcThaR3/openapi.json