> ## 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.

# Compare source overlap

> Compare the sources that support your brand and competitors.

Compare the sources that support your brand and competitors.

**MCP tool:** `compare_grounding_sources`. **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. |
| `brand_set` | string\[] or null | No | `null` | Brand labels whose supporting sources you want to compare. Omit to use the configured target brand and competitors. |
| `top_per_brand` | integer | No | `10` | Maximum leading sources selected for each brand before classifying shared and brand-specific sources. A source outside this selection is not proven absent. Minimum 1. Maximum 200. |
| `aggregation_level` | string | No | `'domain'` | domain requests source-domain results; url requests individual-page results. Keep the same reporting unit when comparing measurements. |
| `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. |

## 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": "compare_grounding_sources",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID",
    "brand_set": [
      "Colorescience",
      "CeraVe"
    ],
    "top_per_brand": 10,
    "aggregation_level": "domain"
  }
}
```

## Read the response

Returned data separates shared, brand-specific, and competitor-specific sources and includes gap signals 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.brand_set` | Brands included in the comparison. |
| `data.aggregation_level` | Source reporting unit requested for the comparison. |
| `data.shared_sources[].domain_or_url` | Source appearing in the selected leading sources for at least two requested brands. |
| `data.shared_sources[].brands` | Brands sharing that source within the selected lists. |
| `data.shared_sources[].estimate` | One contributing brand’s source estimate. It is not a combined estimate across the listed brands. |

## 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": {
    "brand_set": [
      "Colorescience",
      "CeraVe"
    ],
    "aggregation_level": "domain",
    "shared_sources": [
      {
        "domain_or_url": "livetinted.com",
        "brands": [
          "CeraVe",
          "Colorescience"
        ],
        "estimate": {
          "value": 15.7,
          "ci": {
            "lower": 8.2,
            "upper": 28,
            "level": 0.95
          },
          "n": 8,
          "stability": "danger_zone",
          "stability_n": 8
        }
      }
    ]
  }
}
```

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

## Important behavior

Shared and brand-specific labels describe the selected top sources for each brand. A shared-source estimate is copied from one contributing brand’s row, not combined across brands; do not present it as an all-brand rate. Inspect per-brand source reads when that distinction matters.

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: [Compare source overlap](/developers/http/http-compare-grounding-sources). HTTP parameters and defaults can differ.


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