ghl_discover_website
Crawl a website to discover pages for AI training. Specify URL and scope to add them to a knowledge base.
Instructions
Start crawling a website to discover pages for AI training. Returns an operationId — use ghl_get_crawler_status to track progress, then ghl_train_crawler_urls to ingest.
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": {
"knowledgeBaseId": "<knowledgeBaseId>",
"url": "<url>",
"option": "<option>"
},
"name": "ghl_discover_website"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Website URL to start crawling from | |
| option | Yes | Crawl scope: Exact = this URL only; Path = this path and sub-paths; Domain = entire domain | |
| knowledgeBaseId | Yes | Knowledge base ID to add discovered pages to |