Crawl a site by following links
smart_crawlCrawl from a starting URL, following links up to a set depth and page limits to extract content from each page. Filter by URL regex or restrict to the same host to control which pages are visited.
Instructions
Start at a URL, follow links up to a depth/page limit, and return content from each page. Stays on the same hostname by default. Use url_filter to restrict which paths are visited.
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": {
"start_url": "<start_url>"
},
"name": "smart_crawl"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| free_only | No | ||
| max_depth | No | Maximum link depth from start. | |
| max_pages | No | Maximum pages to fetch. | |
| start_url | Yes | Starting URL. | |
| url_filter | No | Regex pattern — only follow links that match. | |
| data_format | No | markdown | |
| rate_limit_ms | No | ms between requests to same domain (default 500 for crawls). | |
| same_host_only | No | Restrict crawl to the starting hostname. | |
| force_bright_data | No |