ScrapeMole Search: web search, news search and autocomplete for AI agents: Web search (SERP results)
webUse when an agent needs to search the web: research, fact finding, finding official pages/docs, competitor or link discovery, grounding an answer with URLs. Returns ranked organic results (position, title, url, domain, snippet; published date or lastCrawled time when the source has one). The top 10 come from Bing's public RSS results; deeper pages (count > 10 or page > 1) come from Brave Search. Supports operators the engines support in q (site:, "exact phrase", -exclude, filetype:). If the primary source is unavailable or off-topic it falls back to Brave Search, then the Mwmbl open index; the response says which source answered (source, sourceUrl, fallbackFrom). Pair with ScrapeMole Reader /v1/read to turn a result URL into Markdown. Empty results = 404, not charged. Paid tool: x402 USDC on Base, $0.002 per successful call; call without payment to receive the PaymentRequired object.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Search query (max 400 chars). Operators like site:example.com, "exact phrase", -word work. | |
| page | No | Result page (1-5); each page is "count" results. | 1 |
| safe | No | Safe search level. | moderate |
| count | No | Number of results (1-20). | 10 |
| market | No | Market/locale as language-COUNTRY, e.g. en-US, en-GB, de-DE, fr-FR, ja-JP (applied on the Bing source). | en-US |