Map Website
mapList URLs on a website without fetching content to avoid overflowing context. Map the site, then scrape only needed pages for precise work.
Instructions
List the URLs on a website without fetching their content. Large sites can overflow your context, so limit defaults to 10; narrow with selectPaths or excludePaths. For precise work, map the site, then scrape_as_markdown only the pages you need.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| geo | No | Geolocation of the desired request, expressed as a country name | |
| url | Yes | Website URL to map | |
| limit | No | Maximum number of URLs to return, 10 by default and at most 500 | |
| locale | No | Locale of the desired request | |
| sitemap | No | Whether to use the sitemap alongside links found on pages, only the sitemap, or skip it | |
| selectPaths | No | Only keep URLs whose path matches one of these patterns, e.g. /blog/* | |
| domainFilter | No | Which links to follow: the same domain, its subdomains too, or any domain | |
| excludePaths | No | Drop URLs whose path matches one of these patterns |