Scrape
scrapeExtract content from any URL as Markdown or HTML. Returns the page's content in the chosen format (Markdown by default) with its title, description and links. Use when you have a URL and need what the page says. Start with fast; use standard for pages that need JavaScript and thorough only for sites that block scrapers. To pull specific fields into JSON use documents; to see the page as an image use screenshot. Cost: fast 1 credit, standard 2 credits, thorough 5 credits, charged only when a call succeeds.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "scrape"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to scrape. | |
| mode | No | Mode: fast (Raw HTTP, no JS. <1s), standard (Full JS rendering. 2-5s), thorough (Anti-bot proxies + JS rendering, waits for late scripts. 15-35s). | |
| output | No | Content format. | markdown |
| timeout | No | Seconds the page may take to load (up to 55). | |
| wait_for | No | CSS selector to wait for (standard and thorough modes). | |
| main_content_only | No | Leave out the page's menus, header and footer (default true). Set false to keep them, such as a site-wide notice or the footer's contact details. |