Crawl site
crawl_siteMap a website into a URL/title/snippet list and cache pages for later fetching; use it to discover and scope site content before extracting pages locally.
Instructions
Map a site (sitemap, else link-following if enabled) into a URL/title/snippet list; pages are cached for fetch_url. A start URL with a path stays under it; include_path '/' crawls the whole site.
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_site"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Site root or docs URL | |
| max_pages | No | Page cap (default 20) | |
| exclude_path | No | Skip URLs under this path prefix | |
| include_path | No | Only URLs under this path prefix; replaces the default scope | |
| same_domain_only | No | Stay on the start domain (default true) |