Connection check
verified live · 20h ago
web-3
Turn any URL into clean Markdown and structured data. Scrape, crawl, search and extract.
Tools
13
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http
Last checked
20h ago
Tools & capabilities
13 toolsRead from the running server on 20h ago.
batch
read-only
urls*
Scrape a list of URLs you already have as one job. Returns a batch id straight away; read it with batch_status. Scrape a list of URLs you already have as one job. Returns a batch id straight away; read it with batch_status.
batch_status
read-only
batchId*
Read a batch started with batch: how far it has got, and the results so far. Read a batch started with batch: how far it has got, and the results so far.
brand
read-only
domain*
A company's brand from its domain: logos for light and dark backgrounds, its real colours, name, description and socials. Answers 'what is this company' far better than a raw page… A company's brand from its domain: logos for light and dark backgrounds, its real colours, name, description and socials. Answers 'what is this company' far better than a raw page dump.
crawl
read-only
url*limitmaxDepth
Discover and scrape a whole site as one job. Returns a crawl id straight away; read it with crawl_status. Use this instead of calling scrape in a loop. Discover and scrape a whole site as one job. Returns a crawl id straight away; read it with crawl_status. Use this instead of calling scrape in a loop.
crawl_status
read-only
crawlId*
Read a crawl started with crawl: how far it has got, and the pages it has scraped. Read a crawl started with crawl: how far it has got, and the pages it has scraped.
extract
read-only
urls*promptschemapreferStructure
Pull typed structured data from one or more URLs by JSON schema or prompt. Pull typed structured data from one or more URLs by JSON schema or prompt.
images
read-only
url*
Harvest a page's images with their metadata, without rendering it. Cheaper than a screenshot and returns the source images rather than a picture of the page. Harvest a page's images with their metadata, without rendering it. Cheaper than a screenshot and returns the source images rather than a picture of the page.
logo
read-only
typethemedomain*
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 you need — it costs a fifth as much and ret… 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 you need — it costs a fifth as much and returns one asset instead of the whole record.
map
read-only
url*limit
Enumerate a site's URLs from its sitemap and links, without scraping them. Enumerate a site's URLs from its sitemap and links, without scraping them.
scrape
read-only
url*formatspreferStructure
Turn a URL into clean, LLM-ready markdown and structured data. Turn a URL into clean, LLM-ready markdown and structured data.
screenshot
read-only
url*maxAgetimeoutwaitForfullPageviewport
+2
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 what it says. 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 what it says.
search
read-only
limitquery*scrapeResultspreferStructure
Search the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra credit per page. Search the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra credit per page.
styleguide
read-only
domain*