Hydrafetch
Hydrafetch gives Claude the live web. Ask about any public page and Claude reads its main content as clean Markdown, with the navigation, banners and boilerplate removed, including pages that only show their content once loaded in a browser. Claude can read a single page, search the web, list every page on a site, crawl a whole site or a list of URLs, and pull fields such as prices, names or dates out of pages as JSON. Ask for a company's brand and you get its logo, colours and fonts as a card in the chat. Ask for a screenshot and you see the page right there, with a full-page view. Hydrafetch only reads public pages and never posts to or changes anything on a site. Usage is billed in credits from your Hydrafetch account, one credit a page for most tools, and failed requests are never charged. New accounts get 500 free credits to use within 30 days. Sign in with your Hydrafetch account to connect.
Choose a connection option
13 tool names reported
Source-declared tools. Availability can depend on the connection and permissions; these are not runtime test results.
Claude connector directory ↗ · Observed 2026-11-01 · Completeness not established
batchbatch_statusbrandcrawlcrawl_statusextractimageslogomapscrapescreenshotsearchstyleguide
Sources and provenance
- Claude connector directoryClaude tier: community · Observed
- Official MCP RegistryObserved
Grouping basis: endpoint. Exact endpoints or package sets can be grouped automatically; other relationships require evidence review. This does not verify publisher affiliation, connection health, or equivalent capabilities.