Read mention statements

Retrieve answer statements that mention selected brand terms. MCP tool: list_mention_statements. Operation: read. Uses the authorized connection; no project or content changes are made by this tool.

Parameters

Name	Type	Required	Default	Meaning and accepted values
`project_id`	string	Yes	`Required`	Project ID from list_projects. Select the project in the intended workspace and environment.
`run_id`	string	Yes	`Required`	Run ID from list_runs for this project. Use the exact returned value and check readiness before reading measurements.
`entities`	string[] or null	No	`null`	Measured names to include. Multiple names select statements mentioning any listed name; they do not require every name in one statement.
`include_ungrounded`	boolean	No	`true`	Include brand statements that have no citation support. False restricts results to grounded statements.
`include_full_response`	boolean	No	`false`	Include the answer containing the statement, subject to max_text_chars.
`max_text_chars`	integer	No	`500`	Character limit applied to returned statement text and, when requested, full response text. Shortened text is not the complete evidence. Minimum 50. Maximum 2000.
`limit`	integer	No	`25`	Maximum statement rows on this page. Continue with data.cursor when supplied. Minimum 1. Maximum 100.
`cursor`	string or null	No	`null`	Next-page value from data.cursor. Keep the project, run, filters, and text settings unchanged when continuing.
`filters`	object[] or null	No	`null`	Select measured answers with objects containing dimension and values. Use labels from list_dimension_options; inspect returned warnings for filters that were not applied.
`prompt_type`	string or null	No	`null`	Select an exact Category facet label returned for the project.
`intent`	string or null	No	`null`	Select an exact Customer Intent facet label returned for the project.
`topic`	string or null	No	`null`	Select an exact measured topic label. A broader phrase does not select every topic containing that phrase.
`query_id`	integer or null	No	`null`	Restrict evidence to one integer query ID returned by list_queries.

Example call

Replace ID placeholders and example selections with values from your account. This is the params object for MCP tools/call.

{
  "name": "list_mention_statements",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID",
    "entities": [
      "Colorescience"
    ],
    "limit": 25,
    "include_full_response": false
  }
}

Read the response

Measurement data.rows contains statement evidence and source information. Use data.cursor for the next page; keep the same filters and text settings.

Fields to use

These selected fields explain the example and the result to preserve. Field presence depends on the response; this is not a complete response schema.

Field	Meaning and use
`data.rows[].platform`	Platform associated with the statement.
`data.rows[].mentioned_terms`	Measured names identified in the statement.
`data.rows[].is_grounded`	Whether the statement has recorded citation support.
`data.rows[].grounding_urls`	URLs recorded as supporting the statement; an empty list has no URLs to cite as evidence.
`data.n_available`	Statement rows available after selection, before the page limit.
`data.cursor`	Opaque value to pass as `cursor` in the next request. A null or absent value means there is no next page.

Response example

Selected fields from an observed IQRush Dev response. Lists are shortened and project/run IDs are placeholders. Omitted fields remain available in the actual response.

{
  "data_ready": true,
  "data": {
    "rows": [
      {
        "platform": "OPENAI",
        "mentioned_terms": [
          "Colorescience"
        ],
        "is_grounded": false,
        "grounding_urls": []
      }
    ],
    "n_available": 280
  }
}

Text and record identifiers are omitted from this excerpt. Retrieve those fields from your own response when preparing an evidence review.

Important behavior

Several requested entities means ANY of them, not all together. A statement can contain multiple sentences. Text can be shortened by max_text_chars, including when full response text is requested. Check tool and payload errors before using the result. Response handling explains estimates and empty results; errors and recovery covers invalid requests and temporary failures. HTTP equivalent: Read mention statements. HTTP parameters and defaults can differ.

Get started

Connect securely

Read measurements

Build dependable integrations

Build reports

Report recipes

Reference

Session and discovery

Visibility measurements

Sources and evidence

Changes and trends

Google data

Pages and report planning

HTTP operations

Read mention statements

Parameters

Example call

Read the response

Fields to use

Response example

Important behavior

​Parameters

​Example call

​Read the response

​Fields to use

​Response example

​Important behavior

Parameters

Example call

Read the response

Fields to use

Response example

Important behavior