Extract page content
browser_extractRead page content as deterministic text, links, or HTML, optionally scoped by a CSS selector, to gather facts or verify an outcome without a model call.
Instructions
Read page content as data, deterministically (free, no model call): mode "text" (default), "links", or "html", optionally scoped by a CSS selector. Use it to gather facts or verify an outcome rather than to act. text collapses whitespace and prefers article/main content; links returns up to 300 {text, href}; html is raw (default cap 100000).
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "browser_extract"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | What to return (default "text"). | |
| selector | No | Optional CSS selector to scope the extraction; omitted = whole page. | |
| max_chars | No | Cap on returned characters (default 20000; HTML 100000). |