Clarification on pagination for the Purview scan endpoint.

Question

Clarification on pagination for the Purview scan endpoint.

Balamurugan, Susinthika 20

Hi Team
We have generated additional scan run data for the below endpoint (100+ records). However, we are still not receiving pagination keys (e.g., nextLink) in the response.

We have attached the request and response for your reference. Could you please provide insights on this endpoint, specifically regarding its default page size and pagination behaviour? This will help us proceed further with validating pagination.

Request Endpoint: https://<domain>.purview.azure.com/scan/datasources/<datasourcename>/scans/<scanname>/runs?api-version=2023-09-01

**Response:

This contains a one sample record and the total count of records from this endpoint.**

JSON

        {
            "discoveryExecutionDetails": {
                "discoveryStartTime": "2026-03-10T06:40:11.4817265Z",
                "discoveryEndTime": "2026-03-10T06:44:29.8952577Z",
                "status": "Succeeded",
                "statistics": {
                    "assets": {
                        "discovered": 72,
                        "classified": 1
                    }
                },
                "isErrorLogAvailable": false
            },
            "ingestionExecutionDetails": {
                "ingestionStartTime": "2026-03-10T06:41:29.6976853Z",
                "ingestionEndTime": "2026-03-10T06:44:36.2151666Z",
                "status": "Succeeded",
                "statistics": {
                    "assets": {
                        "succeeded": 72,
                        "failed": 0,
                        "processing": 0
                    },
                    "relationships": {
                        "succeeded": 0,
                        "failed": 0,
                        "processing": 0
                    }
                },
                "estimatedTimeRemainingInSeconds": null,
                "isErrorLogAvailable": false,
                "lastUpdatedAt": "2026-03-20T07:12:32.6500378+00:00"
            },
            "parentId": null,
            "id": "df404def-14e9-4a7e-822f-5959aafe29d5",
            "ingestionJobId": "df404def-14e9-4a7e-822f-5959aafe29d5",
            "resourceId": null,
            "status": "Succeeded",
            "webScanResults": null,
            "diagnostics": {
                "notifications": [],
                "exceptionCountMap": {}
            },
            "startTime": "2026-03-10T06:40:07.3197594Z",
            "endTime": "2026-03-10T06:44:36.2151666Z",
            "scanRulesetVersion": 3,
            "scanRulesetType": "System",
            "scanScopeType": "L3",
            "scanLevelType": "Full",
            "errorMessage": null,
            "error": null,
            "runType": "Manual",
            "dataSourceType": "AmazonS3"
        }
    ],
    "count": 107

0 comments

2 answers

Your answer

Answer 1

SAI JAGADEESH KUDIPUDI 1,905 Microsoft External Staff Moderator

Hi Balamurugan, Susinthika,
Thanks for the details and JSON sample. Here’s what’s happening with the /scan/.../runs endpoint in Purview:

Default paging behavior
- By design this Data Plane endpoint returns only a single run record by default (think of it as a “head-of-list” snapshot).
- The count field in your response is the total number of runs that exist (107 in your case), not the number of items returned in that single-page payload.
- Because the default page size is 1, the service doesn’t emit a nextLink unless you explicitly ask for more than one item.
How to page through runs
- You can opt into paging by using OData query parameters: • $top to set how many runs you want returned in each page (up to the service limit). • $skip to skip a certain number of runs.
- Example: GET …/runs?api-version=2023-09-01&$top=50
- If you request fewer than or exactly the total count, and there are more runs beyond what you’ve asked for, you’ll get a nextLink in the response pointing at the next page.
Next steps & troubleshooting
- Try calling the endpoint with a $top value (e.g. 50 or 100). If you set $top smaller than count, you should see a nextLink in the payload.
- If you still don’t see nextLink, let me know: • Which API version and region you’re calling? • Exact URL (minus any PII) including the query string you’re using. • Whether you’ve tried both $top and $skip or using the returned nextLink URI.

Hope that helps you validate pagination. Let me know how it goes!

Reference Links:

Hope this helps. If you have any follow-up questions, please let me know. I would be happy to help.

Please do not forget to "Accept Answer" and "up-vote" wherever the information provided helps you, as this can be beneficial to other community members.

Balamurugan, Susinthika 20 Reputation points

2026-03-26T10:13:30.37+00:00
Hi @SAI JAGADEESH KUDIPUDI

Thank you for your response.

We attempted to use the $top=50 query parameter; however, this specific endpoint:

https://<domain>.purview.azure.com/scan/datasources/<datasourcename>/scans/<scanname>/runs?api-version=2023-09-01

does not appear to support any filtering or query parameters.

Additionally, as per the documentation mentioned below, nextLink is mentioned as the pagination token for this endpoint. However, we have not been able to observe this behaviour during our testing.

For reference, we are using the following documentation for this endpoint: https://learn.microsoft.com/en-us/rest/api/purview/scanningdataplane/scan-result/list-scan-history?view=rest-purview-scanningdataplane-2023-09-01&tabs=HTTP

When attempting to use query parameters such as $top, we encountered the following error:

{ "Message": "The query specified in the URI is not valid. The requested resource is not a collection. Query options $filter, $orderby, $count, $skip, and $top can be applied only on collections.", "ExceptionMessage": "The requested resource is not a collection. Query options $filter, $orderby, $count, $skip, and $top can be applied only on collections.", "ExceptionType": "Microsoft.OData.ODataException", "StackTrace": " at Microsoft.AspNet.OData.EnableQueryAttribute.ValidateSelectExpandOnly(ODataQueryOptions queryOptions)\n at Microsoft.AspNet.OData.EnableQueryAttribute.OnActionExecuted(Object responseValue, IQueryable singleResultCollection, IWebApiActionDescriptor actionDescriptor, IWebApiRequestMessage request, Func`2 modelFunction, Func`2 createQueryOptionFunction, Action`1 createResponseAction, Action`3 createErrorAction)" }

Could you please help clarify:

The exact pagination behaviour of this endpoint

Whether nextLink is consistently supported and under what conditions it is returned

If there is any recommended approach to test pagination for this endpoint

This will help us better understand whether pagination can be validated for this API and how to proceed with our implementation.

Thanks in advance for your support.
SAI JAGADEESH KUDIPUDI 1,905 Reputation points Microsoft External Staff Moderator

2026-04-14T16:17:39.44+00:00
Hi Balamurugan, Susinthika,

Thank you for your detailed follow‑up and for testing this further from your end.

We have reviewed your observation along with the official Microsoft Purview Scanning Data Plane REST API behavior for the below endpoint:

GET /scan/datasources/{datasourceName}/scans/{scanName}/runs?api-version=2023-09-01

Based on validation with the Microsoft Purview REST API documentation, we would like to clarify the pagination behavior for this specific endpoint.

Although the API response contract includes the properties such as:

value

count

nextLink

the Microsoft sample response for this endpoint also shows that:

"count": 1, "nextLink": null

This confirms that the nextLink field is conditionally returned by the service and is not guaranteed to be present, even when the total number of scan runs is greater than one.

Additionally, when attempting to use query parameters such as:

$top $skip $filter $orderby

the service returns the following error:

“The requested resource is not a collection. Query options $filter, $orderby, $count, $skip, and $top can be applied only on collections.”

This behavior is expected for this API because the /runs endpoint is not exposed as an OData pageable collection resource. As a result, client‑side pagination parameters such as $top or $skip are currently not supported for this endpoint.

Furthermore, as per Microsoft Purview API pagination design guidance, pagination metadata such as nextLink is returned only when the service internally determines that the response must be split into multiple pages, and there is no supported configuration or request parameter available to enable or force this behavior from the client side.

This means that even when the response contains:

"count": 107

the service may still return:

"value": [ latest run ] "nextLink": null

based on internal service behavior.

Pagination using $top / $skip is not supported for this endpoint, and the nextLink value is not guaranteed to be returned even when the total run count is greater than one. The current behavior you are observing aligns with the intended service design, and there is no additional configuration required from your end

Microsoft Reference Links:

List Scan History – Microsoft Purview REST API

Pagination related queries for Purview API – Microsoft Q&A

Hope this helps. If you have any follow-up questions, please let me know. I would be happy to help.

Please do not forget to "Accept Answer" and "up-vote" wherever the information provided helps you, as this can be beneficial to other community members.

Answer 2

For Microsoft Purview scan listing APIs, pagination is exposed through a nextLink property when there are additional pages of results.

From the documented Purview Scanning models:

ScanListOutput (used by Purview scan list operations) has an optional
```
  nextLink?: string
```
described as:

The link to the next page of results, if any remaining results exist.

The response body schema for list operations is of the form:

  {
    "value": [ ... ],
    "nextLink": "string",
    "count": number
  }

Key implications for the behavior being observed:

count is the total number of items that match the query (in your case, 107).
nextLink is only present when the current response is a partial page and more results remain.
If nextLink is missing or null, the page returned already contains all items for that request, regardless of the count value.

Therefore, if the response contains count: 107 but no nextLink, the service is returning all 107 runs in a single page for that endpoint invocation. In that case:

There is no additional page to request.
Pagination cannot be validated on that dataset because the server has not needed to paginate.

To validate pagination behavior for this API, it is necessary to:

Use a data source/scan with enough runs that the service decides to split results into multiple pages, or
Use a client/SDK that exposes Pageable behavior (for example, PurviewDataSourceClient.GetScans returns Pageable<BinaryData> and internally handles nextLink when present).

Once the service returns a partial page, the response will include nextLink, which can then be followed to retrieve subsequent pages.

References:

Share via

Clarification on pagination for the Purview scan endpoint.

2 answers

Your answer