Product Reviews Extraction

Read visible reviews from a supported public product or review page, including ratings, themes and sentiment.

Pay by wallet (x402) AI-generated product-reviews-extract

Example

Input

{
  "url": "https://www.amazon.com/dp/B0CHX3QBCH"
}

Answer

{
  "url": "https://www.amazon.com/dp/B0CHX3QBCH",
  "source": "amazon.com",
  "common_cons": null,
  "common_pros": null,
  "product_name": "Apple iPhone 15 Plus FineWoven Case with MagSafe - Pacific Blue",
  "review_count": null,
  "average_rating": null,
  "recent_reviews": [],
  "sentiment_summary": "No customer reviews available on this product page",
  "rating_distribution": {
    "1_star": null,
    "2_star": null,
    "3_star": null,
    "4_star": null,
    "5_star": null
  }
}

Inputs

Field	Type	Required	What it is
`url`	string	Yes	Product or review page URL. Sites whose Terms of Service forbid automated access (Trustpilot, Glassdoor, LinkedIn) are rejected without being fetched.

Output fields

How reliably each field appears in a successful answer.

Field	Type	Appears
`common_cons`	array	Always (present in every successful answer)
`common_pros`	array	Always (present in every successful answer)
`review_count`	number	Always (present in every successful answer)
`average_rating`	number	Always (present in every successful answer)
`rating_distribution`	object	Always (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "product-reviews-extract",
    "inputs": {
      "url": "https://www.amazon.com/dp/B0CHX3QBCH"
    },
    "max_price_cents": 25
  }'

{
  "tool": "strale_execute",
  "arguments": {
    "slug": "product-reviews-extract",
    "inputs": {
      "url": "https://www.amazon.com/dp/B0CHX3QBCH"
    },
    "max_price_cents": 25
  }
}

import { Strale } from "straleio";

const strale = new Strale({ apiKey: process.env.STRALE_API_KEY! });
const result = await strale.do({
  capability_slug: "product-reviews-extract",
  inputs: {
    "url": "https://www.amazon.com/dp/B0CHX3QBCH"
  },
  max_price_cents: 25,
});

import os
from straleio import Strale, DoRequest

strale = Strale(api_key=os.environ["STRALE_API_KEY"])
result = strale.do(DoRequest(
    capability_slug="product-reviews-extract",
    inputs={
        "url": "https://www.amazon.com/dp/B0CHX3QBCH",
    },
    max_price_cents=25,
))

# No account. The first request answers 402 with the price in USDC;
# an x402 client pays it from your wallet and repeats the request.
curl -i 'https://api.strale.io/x402/v2/product-reviews-extract?url=https%3A%2F%2Fwww.amazon.com%2Fdp%2FB0CHX3QBCH'

Limitations

Some review sources are unsupported
Trustpilot, Glassdoor and LinkedIn pages are not supported and return a policy error before the page is read. Repeating the same request does not return review data.
What to do instead: Supply a first-party product page with publicly visible reviews.
Hidden or paginated reviews can be missed
Extracts reviews visible on the product page — filtered/hidden reviews and reviews behind 'load more' may not be captured
What to do instead: Request the direct product review page URL rather than the main product page for more complete review coverage
Output size cap per call
Structured output is limited to about 8000 output tokens per call; requests exceeding this limit are refused rather than returned truncated. Requests with large results can exceed this limit, and repeating the same request does not help.
What to do instead: Try a page with fewer reviews — this capability extracts up to ~10 recent reviews per call