Amazon Top Reviews Scraper MCP Server
# Amazon Top Reviews Scraper MCP Server
[](https://www.npmjs.com/package/@mambalabsdev/mcp-amazon-top-reviews-scraper) [](https://github.com/mambalabsdev/mcp-amazon-top-reviews-scraper/blob/main/LICENSE)
An MCP server for the Mamba Labs Amazon Top Reviews Scraper actor on Apify. Top Amazon reviews and rating summary by ASIN on 8 marketplaces outside the US.
## What's Inside
- [What it does](#what-it-does)
- [Quick start](#quick-start)
- [Prerequisites](#prerequisites)
- [Example prompts](#example-prompts)
- [Tool](#tool)
- [Inputs](#inputs)
- [Pricing](#pricing)
- [Full actor documentation](#full-actor-documentation)
- [License](#license)
## What it does
Give ASINs or product URLs on 8 Amazon marketplaces outside the US. You get one row per product with the rating, ratings count, and star split, and one flat row per top review: about 8 from the marketplace country and up to 5 from other countries, with date, stars, title, full text, variant, verified purchase, and helpful votes.
All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.
## Quick start
You need Node.js 18 or newer and an Apify account with an API token.
Add this to your Claude Desktop config (`claude_desktop_config.json`), Cursor, or any MCP client:
```json
{
"mcpServers": {
"mamba-amazon-top-reviews-scraper": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-amazon-top-reviews-scraper"
],
"env": {
"APIFY_TOKEN": "your-apify-token"
}
}
}
}
```
Restart the client. The `get_amazon_top_reviews` tool appears.
## Prerequisites
- Node.js 18 or newer.
- An Apify API token from [console.apify.com/account/integrations](https://console.apify.com/account/integrations), set as `APIFY_TOKEN`. The server lists its tool without a token; a call needs one.
## Example prompts
- "Get the top reviews for ASIN B01N5IB20Q on amazon.de."
- "What do UK buyers say about this Amazon product?"
- "Compare the star split of these ASINs on amazon.co.jp."
## Tool
`get_amazon_top_reviews`. One tool. Example arguments:
```json
{
"products": [
"B01N5IB20Q"
],
"marketplace": "amazon.co.uk"
}
```
## Inputs
Every buyer facing input of the actor. Omitted inputs take the actor's own defaults.
| Input | Type | Required | Description |
|---|---|---|---|
| `products` | array | no | ASINs or Amazon product URLs. A URL sets its own marketplace; an ASIN uses Marketplace below. From Clay, put the column inside a one item list. |
| `marketplace` | string | no | Marketplace for ASINs given without a URL. amazon.co.uk (default), amazon.de, amazon.fr, amazon.it, amazon.es, amazon.ca, amazon.co.jp, or amazon.in. amazon.com is not supported: its logged out pages show no reviews. |
| `include_other_countries` | boolean | no | yes (default) or no. The page also shows about 3 to 5 top reviews from other countries, which can include the United States. No keeps only the marketplace's own country. |
| `include_reviewer_names` | boolean | no | no (default) or yes. Yes adds the public display name Amazon shows on each review. |
| `max_charge_usd` | string | no | Optional. The run stops before a charge that would pass this amount. Summary rows are always returned. |
## Pricing
Pay per event on Apify, billed to your Apify account. Prices in USD.
| Event | Free plan | Bronze | Silver | Gold |
|---|---|---|---|---|
| `product-read`, one product page read, with up to about 13 top reviews | $0.03 | $0.0285 | $0.027 | $0.0255 |
| `product-not-found`, one ASIN Amazon reports as not on that marketplace | $0.002 | $0.0019 | $0.0018 | $0.0017 |
| `apify-actor-start`, per run start | $0.006 | $0.006 | $0.006 | $0.006 |
Review rows, blocked products, and refused input are free. Mamba Labs pays the platform costs of the run, Apify proxy traffic included.
## Full actor documentation
[apify.com/mambalabs/amazon-top-reviews-scraper](https://apify.com/mambalabs/amazon-top-reviews-scraper)
## License
MIT. See [LICENSE](LICENSE).
TDQS
Scored across 1 tool
Only one tool is exposed, so there is no possibility of selecting the wrong tool or confusing overlapping purposes. Its purpose is clearly scoped to retrieving Amazon top reviews.
The single tool name get_amazon_top_reviews follows a clear verb_noun convention and is descriptive. With only one tool, there is no inconsistency across the set.
A single tool is reasonable for a narrowly scoped scraper focused only on top reviews. It is slightly thin compared with typical multi-tool servers, but the tool is not trivial and matches the server's stated purpose.
The tool covers top reviews across several marketplaces and returns useful metadata, but it explicitly lacks the US marketplace, paging, and sorting. Those are notable gaps for an Amazon reviews scraper, even if some are intentional limitations.