Website reader: crawl a site to Markdown
website-readerCrawl up to 10 pages of a website or docs section and get each page back as clean Markdown with title and URL. Built for agents that need a whole site. Use it when: An agent must read a whole small site or a docs section, not just one page: up to 10 pages on the same site, as clean Markdown. Not for: Pages behind a login, very large sites, or apps that only render with JavaScript. Returns: Up to 10 pages, each with its URL, title, description and the page text as Markdown. Typical time: about 50 s. Price: $0.042 per search (up to 10 pages), charged only on success. One call = up to 10 pages.
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": "website-reader"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Where to start, e.g. https://docs.example.com/; links on the same site are followed |