> ## 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 citation scores

> Read citation share or citation coverage for domains or pages.

Read citation share or citation coverage for domains or pages.

**MCP tool:** `get_citation_score`. **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. |
| `metric` | string | No | `'share'` | share requests a source’s share of citations; coverage requests how often responses cite it. Both are proportions. Set this explicitly when comparing interfaces. |
| `aggregation_level` | string | No | `'domain'` | domain requests source-domain results; url requests individual-page results. Keep the same reporting unit when comparing measurements. |
| `group_by` | string\[] or null | No | `null` | For domain results, request platform, topic, intent, or prompt\_type groups. URL results do not apply group\_by in this edition. Check the returned warnings and row labels. |
| `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 sources with kind: leaderboard, all, owned, or specified. For specified, provide domains containing exact source keys for the requested reporting unit. |

## 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_citation_score",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID",
    "metric": "coverage",
    "aggregation_level": "domain",
    "subject": {
      "kind": "owned"
    },
    "group_by": [
      "platform"
    ]
  }
}
```

## Read the response

Measurement envelope with `data.metric`, `data.aggregation_level`, and `data.rows`. Rows include `domain_or_url`, `group_by_values`, `estimate`, source flags, and segment labels 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.metric` | share or coverage, identifying which citation measure was returned. |
| `data.aggregation_level` | domain or url, identifying the source reporting unit. |
| `data.rows[].domain_or_url` | The source measured by this row. |
| `data.rows[].group_by_values` | Dimension labels for this row; preserve them beside its estimate. |
| `data.rows[].estimate` | Value, confidence interval, and row quality. Citation score values and bounds are proportions. |
| `data.filters_applied.warnings` | Scope limitations to review before interpreting a filtered or grouped result. |

## 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": {
    "metric": "coverage",
    "aggregation_level": "domain",
    "rows": [
      {
        "domain_or_url": "colorescience.com",
        "group_by_values": {
          "platform": "VERTEX"
        },
        "estimate": {
          "value": 0.275,
          "ci": {
            "lower": 0.222389,
            "upper": 0.334701,
            "level": 0.95
          },
          "n": 240,
          "stability": "stable",
          "stability_n": 240
        }
      }
    ],
    "filters_applied": {
      "filters": {},
      "group_by": [
        "platform"
      ],
      "warnings": []
    }
  }
}
```

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

## Important behavior

Share and coverage have different denominators. Values and interval bounds use proportions. Use owned/all/specified citation subjects and inspect selection counts.

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 citation scores](/developers/http/http-get-citation-score). HTTP parameters and defaults can differ.


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