# Find similar

> Find pages similar to a URL, in the same result shape as web search.

`find_similar` finds pages similar to a URL you have: competitors of a product site, other coverage of an article, related papers or posts. It returns the same result shape as [`web_search`](https://clonvo.com/docs/web-search.md). To find similar companies with company fields, use [`company_similar`](https://clonvo.com/docs/company-similar.md).

Call it with `POST /v1/tools/find_similar`, or as `find_similar` over [MCP](https://clonvo.com/docs/mcp.md).

## Arguments

-   `url` string Required
    
    The page to find similar pages to.
    
-   `max_results` integer
    
    How many results to return (1–20, default 5).
    
-   `exclude_source_domain` boolean
    
    Leave out pages on the URL’s own domain (default true).
    
-   `include_domains` string\[\]
    
    Only return results from these domains.
    
-   `exclude_domains` string\[\]
    
    Never return results from these domains.
    

## Example

```bash
curl https://api.clonvo.com/v1/tools/find_similar \
  -H "Authorization: Bearer $CLONVO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "arguments": { "url": "https://weaviate.io", "max_results": 3 } }'
```

```json
{
  "id": "gen-01M6A2H8K0M2P4R6T8V0X2Z4B6",
  "tool": "find_similar",
  "provider": "clonvo",
  "result": {
    "url": "https://weaviate.io",
    "results": [
      { "title": "Qdrant - Vector Database", "url": "https://qdrant.tech/", "snippet": "Qdrant is an open-source vector database and vector search engine written in Rust…", "published_at": null, "score": null },
      { "title": "Milvus | High-Performance Vector Database Built for Scale", "url": "https://milvus.io/", "snippet": "Milvus is an open-source vector database built for GenAI applications…", "published_at": null, "score": null },
      { "title": "Chroma", "url": "https://www.trychroma.com/", "snippet": "Chroma is the open-source search and retrieval database for AI applications…", "published_at": null, "score": null }
    ]
  },
  "usage": { "cost": 0.007, "charged": 0.00714, "is_byok": false }
}
```

## Result

| Field | Description |
| --- | --- |
| `url` | The URL you gave. |
| `results[]` | Similar pages, most similar first, with `title`, `url` and `snippet`, and `published_at` and `score` when the provider returns them; the same fields as [`web_search` results](https://clonvo.com/docs/web-search.md#result). |
| `notes` | Present when the provider handled an argument differently. |

The fields around `result` (`id`, `tool`, `provider`, `usage`) are the same for every tool; see [Calling tools](https://clonvo.com/docs/calling-tools.md#response).

## Notes

-   `exclude_source_domain` is on by default, so pages on the URL’s own domain are left out.