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

> One AMC table's columns, each with its type and privacy class — read it before writing SQL against a table you have not used.

Access: **READ** · toolset amazon_ads · family ads.amc-reporting

Amazon Ads API · getDataSource · GET /amc/reporting/{instanceId}/dataSources/{dataSourceId} Docs: https://advertising.amazon.com/API/docs/en-us/amc-reporting#tag/Data-sources/operation/getDataSource

## Call it

MCP tool call:

```json
{
  "name": "ads_get_data_source",
  "arguments": {
    "store": "myStore-US",
    "country_code": "<country_code>",
    "data_source_id": "<data_source_id>"
  }
}
```

Tool API (early access — contact us):

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

## 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. |
| `country_code` | string | yes | the Ads profile's 2-letter country code (e.g. 'US'). |
| `data_source_id` | string | yes | the table name from ads_list_data_sources, e.g. 'sponsored_ads_traffic' or 'conversions'. |

## Result

- `data.columns[]` — {name, data_type, column_type (DIMENSION | METRIC), sensitivity (NONE | LOW | MEDIUM | HIGH | VERY_HIGH | INTERNAL), min_distinct_users, description}.

## Gotchas

- A VERY_HIGH column (user_id, ip_address) can never be in the final SELECT — use it inside COUNT(DISTINCT …) or a join only.
- A result row whose dimension values cover fewer shoppers than min_distinct_users comes back with those dimensions blank; its metrics stay.