Skip to content

Web Fetch

IDweb_fetch
CategoryNetwork
FeaturesNone
DependenciesNone

Fetch content from URLs and convert HTML to markdown or plain text. Powered by FetchKit with built-in SSRF protection, low-noise extraction, bounded crawl discovery, and structured fetchers for common developer and research sources.

Fetch a URL and return its content.

ParameterTypeRequiredDescription
urlstringyesURL to fetch
methodstringnoHTTP method (default: GET)
as_markdownbooleannoConvert HTML to markdown
as_textbooleannoConvert HTML to plain text
content_focusstringnoExtraction mode: full, main, readable, or agent
crawlbooleannoDiscover and fetch a bounded set of same-origin pages
max_pagesintegernoMaximum crawl pages, including the seed (default: 5, maximum: 20)
if_none_matchstringnoETag for a conditional request
if_modified_sincestringnoLast-Modified value for a conditional request
renderstringnoUse rakers for opt-in lightweight JavaScript/DOM rendering
save_to_filestringnoWorkspace destination when file download is enabled for the capability

Returns: content body, status code, metadata, quality signals, redirect history, and crawl summaries when requested.

  • Timeouts: 1s for first byte, 30s for body. Partial content returned on body timeout.
  • Binary content: Images, PDFs, etc. return metadata only (content type, size) — not the binary data.
  • Focused extraction: Use content_focus: "agent" for FetchKit’s lowest-noise extraction strategy.
  • Rendered pages: render: "rakers" runs bounded inline JavaScript without loading page subresources. It is intended for simple rendered pages, not full browser automation.
  • Crawl scope: Crawl discovery stays on the seed URL’s origin and enforces FetchKit’s page limit.
  • SSRF protection: Private IPs (loopback, RFC1918, link-local, CGNAT) are blocked by default with DNS pinning to prevent rebinding attacks.
  • Excessive newlines: Automatically filtered from converted content.