Read a company's site
web_crawlWalk a company's own website and read up to twelve of its pages at once, the pages that say who the firm is and how to reach it first (team, people, leadership, about, contact). Returns each page's words and, across the pages, the e-mail addresses, phone numbers and people the site publishes, each with the page it is on. Use it to find who runs a firm and how to reach them when the database has no people or contacts for it. Members only.
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": "web_crawl"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | A company's own site, as its address or its domain (acme.com). The walk starts there and stays on that site. | |
| find | No | Words to look for on each page, split with "|". Each page then comes back as the passages that hold them. | |
| max_pages | No | How many pages to read, 1 to 12. The pages that say who the firm is and how to reach it (team, people, leadership, about, contact) are read first. |