Search the web and get ranked results with titles, URLs, and snippets. Powered by aggregated search engines (Google, Bing, DuckDuckGo, Brave). Best when you need fresh facts, news, or to find pages to read in detail with scrape_url. Returns up to 50 results with position, title, URL, snippet, source engine, and published date if known.

Fetch a web page and return its main readable content as clean Markdown. Uses Mozilla Readability to strip navigation, footers, ads, and other boilerplate, then converts the article body to Markdown optimized for LLM consumption. Use this instead of web_search when you already know the URL and need to read the full content. Executes JavaScript (headless Chrome) so it handles dynamic / SPA pages.

Capture a screenshot of a web page and return a hosted URL to the image. Supports full-page capture, custom viewport size, device emulation (iPhone/iPad/Pixel/etc.), dark mode, ad/cookie-banner blocking. The returned URL is cached and can be shown to the user or fetched later. Use when you need to visually verify what a page looks like.

Extract title, description, Open Graph tags, Twitter Card data, canonical URL, favicon, and author info from a web page. Much faster than scrape_url when you only need headline information — perfect for link unfurls or quick context before deciding to read the full page.

Render a web page to a PDF document and return the hosted file URL. Supports page size (A4/Letter/etc.), orientation, custom margins, headers/footers. Use for generating reports, archiving pages, or producing printable documentation.

Diff two URLs and get a summary of what changed — added lines, removed lines, modified sections. Modes: 'text' (visible content only), 'structure' (DOM/HTML structural changes), 'full' (both). Great for competitor monitoring, change detection, and verifying deployments.

Analyze a URL for SEO issues and return a scored report. Checks title/description length, heading structure, image alt attributes, link health, meta tags, canonical URL, robots.txt, mobile viewport, load time. Returns errors/warnings grouped by severity with recommendations.

Run an axe-core accessibility audit on a URL. Reports WCAG violations grouped by impact (critical/serious/moderate/minor) with the rule, description, and a link to the fix guide. Use to check pages before launch or to monitor a11y regressions.

Scan a page for broken (4xx/5xx/timeout) links. Returns a summary and the list of broken URLs with their status codes. Great for site maintenance, pre-launch QA, and link-rot monitoring.

Identify which frameworks, libraries, CMS, analytics, and hosting a website uses (similar to Wappalyzer/BuiltWith). Returns technologies grouped by category with version when detectable. Useful for competitor research and sales prospecting.

Generate a Slack/Discord-style link preview card for a URL — title, description, hero image, favicon, site name, author. Lighter than get_metadata and formatted for UI display rather than deep analysis. Useful when an agent needs to show a user what a URL contains.

Resolve DNS records for a domain. Supports A, AAAA, MX, NS, TXT, CNAME, SOA, SRV, CAA, PTR, or ALL (returns all common record types). Useful for debugging DNS config, finding mail servers, or verifying ownership records.

Get WHOIS registration info for a domain — registrar, creation/expiry dates, name servers, ownership (where not redacted), DNSSEC status. Useful for domain research, expiry monitoring, and detecting recently registered domains (often phishing signals).

Inspect a domain's TLS/SSL certificate — issuer, validity dates, days until expiry, SANs, protocol version, cipher. Flags expired, soon-to-expire (<30 days), or self-signed certs. Use for devops monitoring and pre-launch verification.

HTTP-ping a URL and report whether it's up, its status code, response time, any redirects, and server headers. Use for quick uptime checks and debugging 3xx/4xx/5xx responses.