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

> Accept Amazon-generated Sponsored Products campaign recommendations — Amazon applies the proposed change to the campaign.

Access: **DESTRUCTIVE** · toolset amazon_ads · family ads.recommendations

Confirm with the user which ones to accept first. Amazon Ads API · ApplyRecommendations · POST /recommendations/apply Gate: approve, choice — interactive: show the change and the option (Amazon's preview first where one exists), wait for an explicit approve; autopilot: only when the seller's own words asked for this change, within named rule (one option, no tie); otherwise ask.

## Call it

MCP tool call:

```json
{
  "name": "ads_apply_recommendations",
  "arguments": {
    "store": "myStore-US",
    "countryCode": "<countryCode>",
    "body": {}
  }
}
```

Tool API (early access — contact us):

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

## 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. |
| `countryCode` | string | yes | the Ads profile's 2-letter country code (e.g. 'US'). |
| `body` | object | yes | {recommendationIds: [recommendationId, ...]} (1–100) — the recommendationIds from ads_list_recommendations. |

## Result

- 207, one result per item; an item whose code is not "Ok" (or that is listed under error / failures) failed — read its details.
- `data.result.successes[] / data.result.failures[]` — one entry per id sent; read each failure's details.

## Gotchas

- NEW_CAMPAIGN / NEW_VIDEO_CAMPAIGN recommendations are accepted asynchronously — confirm with ads_list_recommendations (STATUS APPLY_SUCCESS or APPLY_FAILED).