Categories › Web & Browser › Scraping, crawling & page-to-text
Web data for agents: YouTube transcripts, screenshots, Google News, WHOIS, jobs, tech stack, more.
Remote server: your requests and data go to siftwright.com. Claude Code: claude mcp add --transport http siftwright-web-data https://siftwright.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
youtube_transcript — Get transcripts (captions) for YouTube videos, Shorts, playlists or channels as plain text and timed segments, with video metadata. Uses thewebsite_screenshot — Capture a PNG or JPEG screenshot, or render a PDF, of public web pages in a real browser. Returns a signed fileUrl per page that can be downgoogle_news — Search Google News for a keyword, company or topic and get articles as structured data (title, link, source, published time). Each article rpqc_scan — Check whether domains use post-quantum TLS key exchange (X25519MLKEM768 / ML-KEM), which groups they prefer, TLS 1.2/1.3 support, certificatcontact_details — Find public emails, phone numbers and social profiles (LinkedIn, X/Twitter, Facebook, Instagram, YouTube) on company websites by crawling uptech_stack — Detect what a website is built with: CMS, ecommerce platform, frameworks, analytics, ad pixels, hosting, CDN, email and DNS provider, with tapp_store_reviews — Get Apple App Store reviews for apps (by name, numeric ID or URL) in one or more countries, filtered by rating, keywords and date. Every 25 ats_jobs — List open jobs from company careers pages on Greenhouse, Lever, Ashby, SmartRecruiters and Recruitee in one schema (title, team, location, rdomain_whois — Look up who a domain is registered with, when it was created, when it expires, its status, nameservers and DNSSEC (from RDAP/WHOIS registrieNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.