Start a crawl
crawlStart an asynchronous site harvest from a seed URL to collect pages at scale; returns an id to poll, with depth, page-count, and pattern filters to scope the run.
Instructions
Start an asynchronous crawl from a seed URL. Returns a crawl_id to poll. Each page is billed; use the estimate tool first to price it.
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": {
"seed_url": "<seed_url>"
},
"name": "crawl"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| dry_run | No | Not supported here: leave it out and use the estimate tool to price a call. | |
| options | No | Other API fields for this operation, merged into the request body as they are (see the Clawifi API docs). | |
| seed_url | Yes | ||
| max_depth | No | ||
| max_pages | No | ||
| exclude_patterns | No | ||
| include_patterns | No | ||
| same_domain_only | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||