Crawl a web page
crawl_pageFetch any public web page and return its content as markdown (default), HTML or text. Gets past common bot walls by switching to a real browser only when needed. Credits by what it took: 1 plain fetch, 3 with JavaScript rendering, 10 for hard-protected sites; nothing when the page could not be fetched.
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": "crawl_page"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The page to fetch (http or https). | |
| format | No | markdown (default), html or text. | |
| wait_for | No | CSS selector to wait for before returning the page. | |
| render_js | No | Render JavaScript in a browser (3 credits). Off by default; the crawler switches to a browser by itself when the page needs one. | |
| country_code | No | 2-letter country to fetch from (default us). |