Find similar pages and websites: like Exa findSimilar
Find pages like a given URL: we read it, search on its title and topic words and return the top 1-20 similar pages (title, URL, snippet, date), leaving out the source site by default. Same filters and contents options as /search (page text, highlights, summaries). Results are for immediate use only (Brave API terms). Use to find competitors, related articles or alternatives to a page.
Inputs
| Name | Type | Description |
|---|---|---|
url (required) | string | The page to find similar pages for |
count | integer | Number of results (1-20, default 10) |
excludeSourceDomain | string | Leave out the source page's whole domain (default true) |
includeDomains | string | Only results from these domains: comma list or JSON array, up to 20 (example.com, github.com/org) |
excludeDomains | string | Never results from these domains: comma list or JSON array |
startPublishedDate | string | Only pages published on or after this date (ISO 8601, e.g. 2025-01-01) |
endPublishedDate | string | Only pages published on or before this date (ISO 8601) |
category | string | news, research paper, github, pdf, tweet, linkedin profile, company, personal site or financial report |
includeText | string | A phrase the results must contain (up to 5 words) |
excludeText | string | A phrase the results must not contain |
textChars | integer | Return the live page text of the top results, this many characters each (500-20000, or true for 3000; default none) |
highlights | string | true: the passages of each page that best match the query, with scores |
numSentences | integer | Sentences per highlight (1-10, default 3) |
highlightsPerUrl | integer | Highlights per result (1-5, default 1) |
summary | string | true: a 1-3 sentence AI summary of each of the top pages |
summaryQuery | string | What the summaries should focus on (default: the query) |
Request
Over HTTP, with a card key from /credits:
curl -H "Authorization: Bearer adt_…" "https://agent-data-tools.revmesh2074.workers.dev/search/similar?url=https%3A%2F%2Fwww.x402.org%2F"
Without a key, the same URL answers 402 Payment Required with x402 and MPP terms, so an agent with a wallet pays per call in USDC (Base, Polygon, Arbitrum or Solana over x402; Base or Tempo over MPP) and retries.
Example result
{
"url": "https://www.x402.org/",
"query": "x402 open payment protocol http stablecoin payments",
"provider": "Brave Search",
"count": 1,
"results": [
{
"title": "HTTP 402 Payment Required",
"url": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/402",
"snippet": "The HTTP 402 Payment Required status code is reserved…",
"age": null,
"publishedDate": null,
"author": null,
"domain": "developer.mozilla.org",
"favicon": null,
"image": null
}
],
"terms": "Results are for the caller's immediate use: no storing or caching beyond the current task, no resale and no model training (Brave Search API terms)."
}
From an AI agent (MCP)
Add the MCP server to Claude, Cursor or any MCP client. This tool is search_similar, and the first 25 successful calls are free:
https://agent-data-tools.revmesh2074.workers.dev/mcp