> ## Documentation Index
> Fetch the complete documentation index at: https://docs.iqrush.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Read groundedness

> Read the extent to which measured brand mention statements have citation support.

Read the extent to which measured brand mention statements have citation support.

**MCP tool:** `get_groundedness`. **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. |
| `aggregation_level` | string | No | `'bundle'` | entity reports individual names; bundle requests configured brand groupings. Read grouping warnings before treating the result as bundled. |
| `group_by` | string\[] or null | No | `null` | Split results into rows by the requested dimensions. Check both filters\_applied.group\_by and each row’s group\_by\_values before labeling the groups. |
| `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. |
| `subject` | string or object or null | No | `null` | Choose brands with kind: leaderboard, all, self, self\_and\_competitors, or specified. For specified, provide entities\_or\_bundles. An unmeasured name is not a measured zero. |

## Example call

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

```json theme={null}
{
  "name": "get_groundedness",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID",
    "aggregation_level": "entity",
    "subject": {
      "kind": "self_and_competitors"
    },
    "group_by": [
      "platform"
    ]
  }
}
```

## Read the response

Measurement rows contain the returned `estimate`, statement counts such as `n_mentions_total` and `n_mentions_grounded`, and additional count or basis fields when available.

### 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[].entity_or_bundle` | Measured name or brand grouping. |
| `data.rows[].group_by_values` | Dimensions identifying the row’s scope. |
| `data.rows[].estimate` | Groundedness value, interval, and quality. Use the returned estimate rather than recomputing a combined rate from counts. |
| `data.rows[].n_mentions_total` | Mention-statement count accompanying the result. |
| `data.rows[].n_mentions_grounded` | Count of those mention statements with citation support. |

## 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.

```json theme={null}
{
  "data_ready": true,
  "data": {
    "aggregation_level": "entity",
    "rows": [
      {
        "entity_or_bundle": "Supergoop",
        "group_by_values": {
          "platform": "OPENAI"
        },
        "estimate": {
          "value": 0.625,
          "ci": {
            "lower": 0.453,
            "upper": 0.771,
            "level": 0.95
          },
          "n": 32,
          "stability": "stable",
          "stability_n": 32
        },
        "n_mentions_total": 32,
        "n_mentions_grounded": 20
      }
    ]
  }
}
```

Read the actual returned scope, counts, and interval levels before interpreting these fields.

## Important behavior

Use `estimate.value`. A combined-platform estimate can differ from `pooled_rate`. Raw occurrences and statement counts are different units. A missing support dataset can make the result unavailable.

Check tool and payload errors before using the result. [Response handling](/developers/guides/09-responses-and-metrics) explains estimates and empty results; [errors and recovery](/developers/guides/13-errors) covers invalid requests and temporary failures.

HTTP equivalent: [Read groundedness](/developers/http/http-get-groundedness). HTTP parameters and defaults can differ.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.