Cloudflare AI Search: give your agents a search engine for your data

Cloudflare's AI Search can give an agent one search interface across several collections of a website owner's material. The service handles crawling and indexing, then combines keyword matching with searches based on meaning. In its announcement, Cloudflare describes using this arrangement to search documentation across its developer ecosystem.

An owner can combine collections through application code or enable public search and MCP endpoints, which let compatible agents query them directly. This reduces the integration work needed to make scattered documentation searchable. Public endpoints allow unauthenticated queries; the article describes adding Cloudflare Access in front of a custom domain when the search should require a login.

“Our goal is to give your agents their own search engine, where they can easily find data to provide better answers for themselves and their humans.”

“We modeled pricing in a way that makes it predictable and scalable: embedding and reranking are free when you use the default models, so no need to worry about predicting token count.”

“It gives coding agents current, cited docs from across the Cloudflare developer ecosystem, so they build on the latest features and fixes instead of stale training data.”

“That replaces the usual fallback (web search then fetching full pages), which is slow, token-heavy, and often lands on the wrong or stale source.”

“Just like Browser Run, it follows robots.txt, identifies itself with an immutable, public user agent, and will respect whatever bot controls a site has in place.”