Sitemap Monitor
Per-user tools — they read and change the sites watched by the key’s owner. Manage the same monitors on the Sitemap Monitor page.
monitor_new_pages
What new pages did the sites I watch publish?List the NEW pages that appeared on the competitor sites this user watches with CitedRank Sitemap Monitor, newest first, with page titles and the time each was first seen. Only pages published after monitoring started are included (the first check is a baseline). Use when the user asks what their competitors published recently, what's new on a watched site, or for a digest of new pages. Pass site to narrow to one watched domain. Follow up with the seo or geo tools on interesting URLs.
| Argument | Type | Description |
|---|
| days | number | Look back this many days (1-365). Default 7. |
| site | string | Optional: only this watched site, as a domain or URL (e.g. 'competitor.com'). |
| limit | number | Max pages to return (1-2000). Default 300. |
Returns: { days, site, pages: [{ url, title, first_seen_at, lastmod, domain, monitor_id }] }
monitor_list
Which sites am I monitoring?List the sites this user watches with CitedRank Sitemap Monitor: domain and path, how many URLs are tracked, new pages in the last 7 days, check interval, last/next check time, status and any error, and whether email alerts are on. Use to answer 'what am I monitoring' or before calling monitor_new_pages for a specific site.
No arguments.
Returns: { monitors: [{ id, target, domain, path_prefix, url_count, new_7d, interval_hours, last_checked_at, next_check_at, last_status, last_error, email_to }], limit }
monitor_add
Start watching a competitor for new pagesStart watching a website for new pages with CitedRank Sitemap Monitor. Give a domain ('competitor.com') to watch its whole sitemap, or a path ('competitor.com/blog/') to watch only that section; sites without a sitemap fall back to the links on that page. The first check (a baseline) runs immediately; new pages are reported from the next check on and emailed to the user. Free plan: up to 20 sites, at most 3 additions per minute.
| Argument | Type | Description |
|---|
| targetrequired | string | Domain or URL to watch, e.g. 'competitor.com' or 'competitor.com/blog/'. |
| interval_hours | 6 | 12 | 24 | 72 | 168 | How often to check, in hours. Default 24. |
| email_alerts | boolean | Email the user when new pages appear. Default true. |
Returns: the created monitor (same shape as an item of monitor_list).
Page & site analysis
Work on any public URL or domain.
sitemap
List every URL on a websiteDiscover every URL on a domain. Parses robots.txt, follows nested sitemap.xml indexes up to 4 levels deep, decompresses .gz, and probes 15+ fallback paths (WordPress, Shopify, Webflow). Returns the URL list with lastmod and priority. Use when the user asks 'what pages does X have' or before bulk-crawling a site.
| Argument | Type | Description |
|---|
| domainrequired | string | Domain or URL to scan (e.g. 'stripe.com'). Only the hostname is used. |
Returns: { domain, sitemaps[], total_urls, urls: [{ url, lastmod, priority }] }
crawl
Get the text content of a pageFetch a single page and return its content as clean Markdown plus a list of image URLs. Renders JavaScript via headless Chromium. Use when the user wants the actual text content of a page (for reading, RAG ingestion, summarization). Cached: re-running on the same URL returns instantly with from_cache=true.
| Argument | Type | Description |
|---|
| urlrequired | string | Full URL to fetch (https://...). |
| refresh | boolean | Force re-render instead of using cache. Default false. |
Returns: { url, status, title, word_count, html_size, mhtml_saved, from_cache, ok }
seo
Audit a URL for SEO problemsRun a 10-section SEO audit on a single URL: title length, description, canonical, headings (h1-h6), Open Graph + Twitter cards, hreflang, link graph (internal/external/nofollow), JSON-LD schema types, media (img/video/iframe + alt-text coverage), content metrics (word count, text-to-HTML ratio), tech (doctype, AMP, scripts), robots meta. Use for SEO diagnosis and competitor audits.
| Argument | Type | Description |
|---|
| urlrequired | string | Full URL to audit. |
| refresh | boolean | Force re-fetch. Default false. |
Returns: a 10-section report: basics, headings, social, i18n, links, schema, media, content, tech, robots_meta.
geo
Check if a page is AI-search (GEO) readyRun a GEO (Generative Engine Optimization) audit on a single URL — scores how easily AI search engines (ChatGPT, Perplexity, Gemini, Claude, Google AI Overviews) can extract and cite the page. Grades seven content-quality dimensions (entity clarity, citable facts, FAQ coverage, structure, authority, comparison positioning, freshness), adjusted for the detected page type. Returns a normalized 0-100 score, a grade, the per-dimension breakdown, a core-page minimum-requirements checklist, and a prioritized fix list. Use when the user asks whether a page is ready for AI search, ChatGPT, or Google AI Overviews.
| Argument | Type | Description |
|---|
| urlrequired | string | Full URL to audit for GEO. |
| refresh | boolean | Force re-fetch. Default false. |
Returns: { url, domain, page_type, score, grade, signals[] (7 dimensions, 0-10 each), requirements, recommendations[], llms_txt }
clone
Extract a site's web UI — colors, fonts, CSSExtract a website's web UI and design system: colors (clustered by hue, primary/accent/neutral roles assigned), font families, font-size scale, border-radius scale, shadow tiers. Returns design tokens ready for export to Tailwind config / CSS variables / JSON. Use for design reverse-engineering, brand audits, building style guides. Shown in the CitedRank UI as the 'Web UI' extractor.
| Argument | Type | Description |
|---|
| urlrequired | string | Full URL to extract the UI from. |
| refresh | boolean | Force re-fetch. Default false. |
Returns: { url, screenshot_available, mhtml_available, css_count, tokens, spec } — spec holds clustered design tokens (colors, typography, spacing, radii, shadows).