Federated image search across license-aware providers (Wikimedia Commons, Openverse, Unsplash, Pexels, Pixabay, iTunes, MusicBrainz CAA, Spotify, Brave). Returns concise ranked candidates with license + attribution. Does NOT auto-download — call download_image after. Default safe-only policy includes open, platform-license, editorial/press tags and rejects UNKNOWN. Use open-only for CC/public-domain only. For large batches, prefer CLI: webfetch batch --jsonl --continue-on-error.

Specialized image search for a musical artist. kind selects provider set + query expansion: 'portrait' (Wikimedia + Unsplash + Spotify), 'album' (MusicBrainz CAA + iTunes + Spotify), 'logo' (Wikimedia), 'performing' (Wikimedia + Pexels). Prefer this over search_images when building artist/band content.

Find canonical album artwork. Uses MusicBrainz Cover Art Archive + iTunes + Spotify. Results are EDITORIAL_LICENSED — safe for album identification UI per platform ToS; always show attribution.

Download an image URL (typically from a prior search_images result) to the local disk cache. Streams with a 20MB hard cap, content-type guard, SHA-256 hash, and returns the cached file path. Host blocklist enforced.

Given an arbitrary URL (image or webpage), determine its license via host heuristics + page metadata (, dc.rights, og tags). Set probe: true to also download the bytes. Use when an agent already has a URL and needs a go/no-go decision before shipping.

Reverse-image-search: given a public image URL, find visually similar images. Requires SERPAPI_KEY env var and providers: ['serpapi']. Returns candidates with heuristic licenses — treat results as leads, not shippable.

Given a webpage URL, return every on the page with inferred dimensions and a heuristic license per image. Respects robots.txt by default. Use to triage a candidate source page before picking.