mcpserver.lol
registry/web-3
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 tools

Read 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.
batch_status read-only batchId*
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…
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.
crawl_status read-only crawlId*
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.
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.
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…
map read-only url*limit
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.
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.
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.
styleguide read-only domain*
A site's design system read from computed styles in a real browser: colours by role with contrast ratios, the type scale, corner radius and button styling. Values defined through C…