Amazon Review Aggregates & Extended History Scraper: MCP config, n8n workflow and API

{
  "productUrls": [
    "https://www.amazon.com/dp/B09X7MPX8L"
  ],
  "maxProductsToDiscover": 10,
  "extendedHistory": true,
  "includeAggregates": true,
  "country": "amazon.com",
  "maxReviews": 15,
  "sortBy": "helpful",
  "verifiedPurchasesOnly": false,
  "mediaReviewsOnly": false,
  "includeImages": true,
  "includeGdprSensitive": false
}

---
name: amazon-review-aggregates-and-extended-history
description: "One record per collected Amazon customer review — rating, title, body, verified-purchase/Vine flags, helpful-votes count, reviewer location, sentiment hint, images/videos, the pipeline that produced the row (`source`: productPage / extendedHistory / cookieMode), its marketplace, a stable dedup fingerprint, and product/source metadata. Runs the Apify Actor dataspryva/amazon-review-aggregates-and-extended-history. Use when the user needs Amazon data with fields such as productAsin, reviewedProductAsin, ratingScore, reviewTitle, reviewDescription, isVerified and an Apify token is available."
compatibility: "Needs network access, curl, and an APIFY_TOKEN environment variable. Runs are billed to the token owner's Apify account."
metadata:
  actor: "dataspryva/amazon-review-aggregates-and-extended-history"
  store-url: "https://apify.com/dataspryva/amazon-review-aggregates-and-extended-history"
---

# Amazon Review Aggregates & Extended History Scraper

Use this skill to fetch Amazon data with the Apify Actor `dataspryva/amazon-review-aggregates-and-extended-history` and work with the returned rows.

## Before running

1. Check that `APIFY_TOKEN` is set in the environment. Never print it or write it to a file.
2. Build `input.json` from the user's request using the fields below. Keep limits small for a first run.
3. Confirm the search terms or URLs with the user if the request is ambiguous.

## Input fields

| Field | Type | Meaning |
| --- | --- | --- |
| `productUrls` | array | List of Amazon product URLs to scrape reviews from. Supports /dp/, /gp/product/, /gp/aw/d/ and /product/ URL formats across 19+ Amazon domains. A bare 10-character ASIN (e.g. |
| `keywords` | array | Search keywords used to auto-discover products when `productUrls` is empty (e.g. "wireless earbuds"). Fetches Amazon's public `/s?k=` search results page for each keyword and reviews up to `maxProductsToDiscover` resulting products. |
| `categoryUrls` | array | Advanced mode: supply your own Amazon `/s?...` or `/b?node=...` category/search URL(s) directly (used only when `productUrls` is empty). Products are discovered the same way as `keywords`. |
| `maxProductsToDiscover` | integer | Maximum number of products to discover per run from `keywords`/`categoryUrls`. Ignored when `productUrls` is supplied directly. |
| `extendedHistory` | boolean | Merge Amazon's public extended review feed for each ASIN (no login, no cookie): up to 100 reviews per star/sort bucket, and walking every bucket yields 100-850+ unique reviews for popular US products, deduplicated against the product-page sample. |
| `mergeMarketplaces` | array | Additional Amazon marketplaces whose product page is fetched for the same ASIN and whose reviews are merged (deduplicated by review ID and content). Each marketplace typically adds a handful of locally-written reviews. |
| `includeAggregates` | boolean | Emit one additional `amazon_review_aggregate` record per product with the product title, average rating, global ratings count, star histogram (plus derived per-star counts), and "Customers say" AI summary with aspects -- parsed from the same page HTML… |
| `country` | string | Amazon country domain to scrape from. URLs from a different domain are honored automatically. |
| `maxReviews` | integer | Hard cap on the number of reviews returned per product AFTER merging and deduplication (1-2000). The product-page sample alone yields ~8-13; the extended review feed can add 100-850+ for popular US products. |
| `sortBy` | one of `helpful`, `recent` | How to sort the returned reviews: most helpful first, or most recent first. |
| `verifiedPurchasesOnly` | boolean | Keep only reviews carrying Amazon's Verified Purchase badge. Applied server-side for the extended feed and client-side for product-page rows. |
| `filterKeywords` | array | Keep only reviews whose title or text contains at least one of these keywords (case-insensitive). Empty = no keyword filter. |
| `reviewsNewerThan` | string | Keep only reviews dated on or after this date (e.g. 2026-01-15 or any ISO date). Reviews whose localized date cannot be parsed are kept. Empty = no date filter. |
| `mediaReviewsOnly` | boolean | Keep only reviews that include at least one reviewer-uploaded image or video. |

Example `input.json` (the Actor's published prefill):

```json
{
  "productUrls": [
    "https://www.amazon.com/dp/B09X7MPX8L"
  ],
  "maxProductsToDiscover": 10,
  "extendedHistory": true,
  "includeAggregates": true,
  "country": "amazon.com",
  "maxReviews": 15,
  "sortBy": "helpful",
  "verifiedPurchasesOnly": false,
  "mediaReviewsOnly": false,
  "includeImages": true,
  "includeGdprSensitive": false
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/dataspryva~amazon-review-aggregates-and-extended-history/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d @input.json > results.json
```

The call waits for the run to finish and returns the dataset items as a JSON array. If the run needs more than 300 seconds the API answers with HTTP 408; then start the run with `POST /v2/acts/dataspryva~amazon-review-aggregates-and-extended-history/runs`, poll `GET /v2/actor-runs/{runId}` until `SUCCEEDED`, and read `GET /v2/datasets/{defaultDatasetId}/items`.

## Output

Each item is one record. Published fields include: `productAsin`, `reviewedProductAsin`, `ratingScore`, `reviewTitle`, `reviewDescription`, `isVerified`, `isVineVoice`, `reviewedIn`, `reviewReaction`, `variant`, `reviewImages`, `position`, `reviewId`, `reviewUrl`, `helpfulCount`, `reviewDate`, `reviewLocation`, `sentimentHint`, `wordCount`, `hasImages`.

Summarise what was found, cite the record URLs when present, and say how many items came back. Do not invent values for empty fields.