Categories › Web & Browser › Scraping, crawling & page-to-text
Clean web data for agents: any URL to Markdown or JSON, plus search, crawls and company brand data.
Remote server: your requests and data go to api.hydrafetch.com. Claude Code: claude mcp add --transport http hydrafetch https://api.hydrafetch.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
scrape — Fetch one web page and return its main content as clean markdown, with optional HTML, links or structured data. Use it to read a page whose map — List the URLs on a website, found through its sitemap and links, without fetching their content. Use it to see which pages exist before choocrawl — Discover and scrape the pages of a website as one background job, following its links from a starting URL. Returns a crawl id straight away;crawl_status — Read a crawl started with crawl: its progress, and one page of the scraped results. When nextOffset is not null, pass it as offset to read tbatch — Scrape a list of URLs you already have, such as pages found with map. Waits for the batch to finish and returns the first page of results inbatch_status — Read a batch started with batch: its progress, and one page of results in the order the URLs were sent. When nextOffset is not null, pass itjobs_search — Search open jobs collected from company career sites and hiring platforms, by whole words in the job title, with optional location, remote acompany_hiring_changes — What changed in companies' hiring since a date: jobs open now, opened and closed, by department, seniority and location, with the postings tsearch — Search the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra creditnews — Find recent news articles about a query, newest first, each with its outlet and publish time. Use it for announcements such as funding roundbrand — A company's brand from its domain: logos for light and dark backgrounds, its colours, name, description and social profiles. Use it to answelogo — A company's logo as a directly embeddable image URL, chosen for the background you name. Use this rather than brand when the mark is all youextract — Pull specific fields out of one or more pages as JSON, shaped by a JSON schema or described in a prompt. Use it when you need values such asstyleguide — A site's design tokens read from computed styles in a real browser: colours by role with contrast ratios, the dark theme colours when the siscreenshot — Render a page in a real browser and capture a PNG, returning its public URL. Use when the question is what the page looks like rather than wimages — Harvest a page's images with their metadata, without rendering it. Cheaper than a screenshot and returns the source images rather than a picjob_status — Get the result of a call that answered with a jobId and status "running" because it needed more time. Returns the same result the call wouldfeedback — Tell Hydrafetch whether an earlier result was accurate. Use it after a scrape, search or other call returns missing, wrong or blocked contenNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.