# customerFeedback_getItemReviewTopics (https://sellersheetai.com/docs/mcp-api/tools/customerFeedback_getItemReviewTopics)

> The 10 most positive and 10 most negative review topics of one ASIN (US, UK, FR, IT, DE, ES, JP only), each with review snippets, occurrence %, star-rating impact and the browse-no

Access: **READ** · toolset amazon_sp · family sp.customerFeedback_2024-06-01

de benchmark. Call it TWICE per ASIN — sortBy MENTIONS (recent ~6 months: what customers mention most) and sortBy STAR_RATING_IMPACT (~18 months: what moves the star rating). Then customerFeedback_getItemReviewTrends. Amazon SP-API · getItemReviewTopics · GET /customerFeedback/2024-06-01/items/{asin}/reviews/topics

## Call it

MCP tool call:

```json
{
  "name": "customerFeedback_getItemReviewTopics",
  "arguments": {
    "store": "myStore-US",
    "asin": "<asin>",
    "sortBy": "MENTIONS"
  }
}
```

Tool API (early access — contact us):

```bash
curl -X POST https://api.sellersheetai.com/api/v1/tools/customerFeedback_getItemReviewTopics \
  -H "Authorization: Bearer $SELLERSHEET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"store":"myStore-US","asin":"<asin>","sortBy":"MENTIONS"}'
```

## Arguments

| Name | Type | Required | Description |
|---|---|---|---|
| `store` | string | yes | the store ref `<store>-<CC>` (name-country, e.g. 'myStore-US') — one of get_user_context's store_refs, verbatim. |
| `asin` | string | yes | the ASIN (e.g. 'B0XXXXXXXX'). |
| `sortBy` | string | yes | the metric the topics are ranked by — one per call, each described above. Allowed: MENTIONS \| STAR_RATING_IMPACT. Allowed: MENTIONS \| STAR_RATING_IMPACT. |
| `summarize` | boolean |  | true returns the slim shape below (~90 % smaller) — use it in AI workflows; default false returns Amazon's raw payload. |

## Result

- `data.reviewTopics` — raw — {asin, itemName, marketplaceId, countryCode, dateRange: {startDate, endDate}, topics: {positiveTopics: [Topic], negativeTopics: [Topic]}} (up to 10 each), Topic = {topic (e.g. 'Assembly/Installation'), asinMetrics: {numberOfMentions, occurrencePercentage (% of this ASIN's reviews mentioning it), starRatingImpact (star points the topic adds or removes)}, parentAsinMetrics (the same over the parent's children), browseNodeMetrics: {occurrencePercentage: {allProducts}, starRatingImpact: {allProducts}} (the CATEGORY benchmark),
- `data.reviewTopics.childAsinMetrics` — {mostMentions: {asin, numberOfMentions}, leastMentions: {asin, numberOfMentions}}, reviewSnippets: [str], subtopics: [{subtopic, metrics: {numberOfMentions, occurrencePercentage}, reviewSnippets}]}. Slim — {topics: {positiveTopics: [SlimTopic], negativeTopics: [SlimTopic]}}, SlimTopic = {topic, asinMetrics, browseNodeMetrics, reviewSnippets (top 3), subtopics (top 3, {subtopic, occurrencePercentage}), gap_ratio (asinMetrics.occurrencePercentage ÷ the category allProducts, null when either is missing — above 1 the ASIN over-indexes; on a NEGATIVE topic that is worse than the category), gap_class CRITICAL (>2×) | HIGH (>1.5×) | MEDIUM (>1×) | LOW (≤1×) | null, or the low-sample class (fewer than 5 mentions of the topic or 10 across the ASIN — gap_ratio is then null), cat_source browse_node | item_payload (where the category figure came from)}; parentAsinMetrics, childAsinMetrics and anything beyond the top 3 are dropped.