dev.onpage/onpage

Est-ce que dev.onpage/onpage est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.onpage/onpage » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 37 outils

• accessibility≈ 280 tokens

  Accessibility for people and the European Accessibility Act. Pick with mode: wcag = WCAG 2.1 AA checks. Needs url. screen_reader = The page as a screen reader reads it. Needs url.

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • mode · string · optionnel · wcag | screen_reader
    Default wcag.
  • tree · object · optionnel
    Optional: an accessibility snapshot from your own browser (role, name, level, children), for example Puppeteer page.accessibility.snapshot().
  • detail · string · optionnel · full | brief
    brief = short summary.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "accessibility", "arguments": {"url": "texte", "mode": "wcag", "tree": {}, "detail": "full", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ai_visibility≈ 783 tokens

  Whether AI assistants can read, quote and recommend a site. Pick with mode: check = AI crawler access, llms.txt, 15 citability checks and the page as a model reads it. Needs url. bots = Fetch the page as Googlebot, GPTBot, ClaudeBot, PerplexityBot and more against a browser: firewall blocks, challenges, cloaking. Needs url. gaps = Where AI answers name competitors, not you, from Brand Radar or similar. Needs site, brand, responses[{question, response, links, search_queries, engine, volume}]. citations = What pages cited by AI do differently, from citation counts. Needs pages[{url, chatgpt, perplexity, gemini, google_ai_overviews, google_ai_mode}].

  Paramètres, retour & exemple (10)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • mode · string · optionnel · check | bots | gaps | citations
    Default check.
  • site · string · optionnel
    Your site, for example example.com.
  • brand · string · optionnel
    Your brand name as people write it.
  • pages · array · optionnel
  • detail · string · optionnel · full | brief
    brief = short summary.
  • source · string · optionnel · ahrefs | semrush | other
    Where the citation counts come from.
  • responses · array · optionnel
  • memory_key · string · optionnel
    site_memory key, records this call.
  • competitors · array · optionnel

  Exemple d'appel

  {"name": "ai_visibility", "arguments": {"url": "texte", "mode": "check", "site": "texte", "brand": "texte", "pages": [], "detail": "full"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• answer_readiness≈ 429 tokens

  Whether a page answers the questions people ask AI and Google. Pick with mode: questions = Sub-questions AI Mode fans out to, and which the page answers. Needs url, topic, questions. passages = The passages that answer given questions, or the gaps. Needs url, question. format = Answer format against the pages that rank. Needs url, question, competitors.

  Paramètres, retour & exemple (8)

  Paramètres

  • url · string · optionnel
    Full address of the page.
  • mode · string · optionnel · questions | passages | format
    Default questions.
  • topic · string · optionnel
    The topic or main query, for example 'passport renewal'.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • question · string · optionnel
    The question people ask, for example 'how long does shipping take to Germany'.
  • questions · array · optionnel
    The sub-questions an AI search engine would ask for the topic.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • competitors · array · optionnel
    Optional: up to 2 pages that rank for the topic.

  Exemple d'appel

  {"name": "answer_readiness", "arguments": {"url": "texte", "mode": "questions", "topic": "texte", "detail": "full", "question": "texte", "questions": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• backlinks≈ 1110 tokens

  Turn backlink data from Ahrefs, Semrush or similar into links won back, won or cleaned up. Pick with mode: broken = Broken and lost backlinks and 404 visits into 301s and outreach. Needs rows[{target_url, source_url, anchor, domain_rating, dofollow, http_code}]. opportunities = Sites linking to competitors, and unlinked brand mentions. Needs site. outreach = One outreach email per site, as drafts for the user's mail after approval. Needs your_site, prospects[{page, type, your_url, dead_url, anchor, contact}]. disavow = A conservative disavow.txt, only after a manual action or clear negative SEO. Needs rows[{url_from, domain, is_spam, domain_rating, anchor, traffic}], reason.

  Paramètres, retour & exemple (16)

  Paramètres

  • mode · string · optionnel · broken | opportunities | outreach | disavow
    Default broken.
  • rows · array · optionnel
    Broken backlink rows, one per linking page.
  • site · string · optionnel
    Optional: your site's address.
  • brand · string · optionnel
    Brand name to look for in mention pages.
  • yours · array · optionnel
    Your own referring domains.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • format · string · optionnel · redirects | nginx | apache | nextjs | csv
    Rule format, default redirects (Cloudflare Pages and Netlify _redirects).
  • reason · string · optionnel · manual_action | negative_seo | other
    Why a disavow is considered.
  • audit_id · string · optionnel
    Optional: a finished site audit, to match on page titles too.
  • mentions · array · optionnel
    Pages that mention the brand.
  • live_urls · array · optionnel
    Optional: your live pages, instead of reading the sitemap.
  • prospects · array · optionnel
  • your_site · string · optionnel
    Your site or brand name, e.g.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • competitors · array · optionnel
    Each competitor with its referring domains.
  • sender_name · string · optionnel
    Name to sign with.

  Exemple d'appel

  {"name": "backlinks", "arguments": {"mode": "broken", "rows": [], "site": "texte", "brand": "texte", "yours": [], "detail": "full"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_keyword≈ 455 tokens

  How pages target a keyword. Pick with mode: focus = One page against one keyword: 8 checks. Needs url, keyword. cannibalization = Your pages competing for one keyword, side by side on every signal, with the plan. Needs keyword, target_url.

  Paramètres, retour & exemple (8)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • mode · string · optionnel · focus | cannibalization
    Default focus.
  • rows · array · optionnel
    Optional Search Console rows for the keyword, to find the competing pages and their positions.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • keyword · string · optionnel
    The search term the page should rank for, for example 'running shoes'.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • target_url · string · optionnel
    The page that should rank for it.
  • competing_urls · array · optionnel
    Other pages of the same site that compete for the keyword.

  Exemple d'appel

  {"name": "check_keyword", "arguments": {"url": "texte", "mode": "focus", "rows": [], "detail": "full", "keyword": "texte", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_links≈ 306 tokens

  Status of URLs and links. Pick with mode: urls = Status, redirect chain and canonical of a list of URLs. Needs urls. outbound = Dead or moved links from a page to other sites, with archived copies. Needs url.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    The page to check.
  • mode · string · optionnel · urls | outbound
    Default urls.
  • urls · array · optionnel
    Addresses to check.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • expected · array · optionnel
    Optional expected final address for each URL, in the same order.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "check_links", "arguments": {"url": "texte", "mode": "urls", "urls": [], "detail": "full", "expected": [], "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• compare≈ 471 tokens

  Compare pages side by side. Pick with mode: pages = Your page against up to 3 competitors. Needs url, competitors. html = Two versions of HTML before and after. Needs before, after. preview = Deploy preview against production before merging. Needs preview_url, production_url.

  Paramètres, retour & exemple (12)

  Paramètres

  • url · string · optionnel
    Full address, for example https://example.com.
  • mode · string · optionnel · pages | html | preview
    Default pages.
  • after · string · optionnel
    HTML after the change.
  • paths · array · optionnel
    Paths like /pricing, default /.
  • before · string · optionnel
    HTML before the change.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • keyword · string · optionnel
    Optional search term to compare keyword use.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • competitors · array · optionnel
    Competitor page addresses.
  • preview_url · string · optionnel
    The deploy preview URL.
  • bypass_token · string · optionnel
    Vercel protection bypass secret.
  • production_url · string · optionnel
    The live site.

  Exemple d'appel

  {"name": "compare", "arguments": {"url": "texte", "mode": "pages", "after": "texte", "paths": [], "before": "texte", "detail": "full"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• content≈ 938 tokens

  What to write and how, in the site's own voice, from the pages that rank and the user's search data. Pick with mode: brief = A content brief from the pages that rank. Needs keyword, competitors. topics = Search Console queries into topics, with the page that owns each, and keyword gaps. Needs rows[{query, page, clicks, impressions, position, url}]. intent = Your page against the search intent of the pages that rank. voice = Learn how the site writes from its best articles. Needs urls. calendar = A dated calendar of refreshes and new pages, steered by what worked here. draft = A draft against the site's voice, sources and SEO, before approval. Needs html.

  Paramètres, retour & exemple (17)

  Paramètres

  • url · string · optionnel
    Optional: your existing page for this term.
  • html · string · optionnel
    The draft as HTML, title in <title> or <h1>.
  • mode · string · optionnel · brief | topics | intent | voice | calendar | draft
    Default brief.
  • rows · array · optionnel
    Search Console rows by query and page.
  • urls · array · optionnel
    The site's own best articles, ones that rank and that the owner likes.
  • ideas · array · optionnel
    Topics without a page yet.
  • start · string · optionnel
    First day, YYYY-MM-DD, default today.
  • weeks · number · optionnel
    Weeks to plan, default 8.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • keyword · string · optionnel
    The search term the page should rank for.
  • queries · array · optionnel
    Search Console rows by query and page, for the site-wide check.
  • audit_id · string · optionnel
    Optional: a finished site audit, for internal link suggestions.
  • per_week · number · optionnel
    Items per week, default 2.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • competitors · array · optionnel
    Pages that rank for the term.
  • webhook_url · string · optionnel
    Optional https Slack or Discord webhook for a Monday reminder; off stops it.
  • competitor_rows · array · optionnel
    Optional keyword gap: competitors' organic keywords (Ahrefs organic-keywords or Semrush domain_organic for each competitor, or Semrush keyword gap rows).

  Exemple d'appel

  {"name": "content", "arguments": {"url": "texte", "html": "texte", "mode": "brief", "rows": [], "urls": [], "ideas": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• dashboard≈ 655 tokens

  A daily SEO data feed for key pages and a live dashboard in the chat. Pick with mode: feed = Start a daily feed of key pages; returns feed_id. Needs url. data = The feed as clean tables over time. Needs feed_id, dataset. build = Blueprint for a live SEO command center with realtime GA4 visitors. Needs feed_id.

  Paramètres, retour & exemple (15)

  Paramètres

  • to · string · optionnel
    End date, YYYY-MM-DD.
  • url · string · optionnel
    Home page of the site.
  • from · string · optionnel
    Start date, YYYY-MM-DD.
  • mode · string · optionnel · feed | data | build
    Default feed.
  • name · string · optionnel
    Optional name, for example the client's name.
  • pages · array · optionnel
    Optional key pages to track, up to 10.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • format · string · optionnel · blueprint | html
    blueprint (default) for Claude Dashboards, or html for a complete, designed dashboard page filled with the feed's data, ready to show as an artifact.
  • dataset · string · optionnel · overview | pages | issues | open_issues | vitals | ai_access | fixes
  • feed_id · string · optionnel
    Feed from create_dashboard_feed.
  • replace · boolean · optionnel
    Replace this connection's existing feed.
  • sources · array · optionnel
    What the user has connected in Claude.
  • bigquery · object · optionnel
    Optional, for ready SQL.
  • fix_log_id · string · optionnel
    Optional fix log from log_fix, to include shipped fixes.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "dashboard", "arguments": {"to": "texte", "url": "texte", "from": "texte", "mode": "feed", "name": "texte", "pages": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• edge_worker≈ 318 tokens

  Fixes applied at the edge on the user's own Cloudflare, on any CMS. Pick with mode: rules = One Worker that fixes a whole section by rules. Needs audit_id. prerender = Serve rendered HTML to AI crawlers for JavaScript apps. Needs url.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    A page of the app, for example https://app.example.com/pricing.
  • mode · string · optionnel · rules | prerender
    Default rules.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • audit_id · string · optionnel
    Id of a completed site audit (start_site_audit, then get_site_audit until complete).
  • site_name · string · optionnel
    Brand name for title endings, for example 'Acme Shoes'.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "edge_worker", "arguments": {"url": "texte", "mode": "rules", "detail": "full", "audit_id": "texte", "site_name": "texte", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• entity≈ 234 tokens

  How Google understands who is behind a site. Pick with mode: graph = Organization, sameAs, logo and founder in structured data. Needs url. trust = Author, about, contact and policy signals. Needs url.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · optionnel
    Full address, for example https://example.com/blog/post.
  • mode · string · optionnel · graph | trust
    Default graph.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "entity", "arguments": {"url": "texte", "mode": "graph", "detail": "full", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• explain_google≈ 921 tokens

  Explain what Google Search Console and Bing Webmaster Tools report, and what to do. Pick with mode: index_status = Index coverage and rich result statuses, with the fix. Needs rows[{url, coverageState, verdict, indexingState, robotsTxtState, pageFetchState}]. manual_action = A manual action, with the cleanup plan and reconsideration draft. Needs action. bing = Bing Webmaster crawl issues, and Bing against Google per query.

  Paramètres, retour & exemple (10)

  Paramètres

  • mode · string · optionnel · index_status | manual_action | bing
    Default index_status.
  • rows · array · optionnel
  • site · string · optionnel
    The site or Search Console property.
  • action · string · optionnel
    The manual action as Search Console shows it.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • issues · array · optionnel
    Bing crawl or index issues.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • sample_urls · array · optionnel
    Example URLs Google listed.
  • bing_queries · array · optionnel
  • google_queries · array · optionnel

  Exemple d'appel

  {"name": "explain_google", "arguments": {"mode": "index_status", "rows": [], "site": "texte", "action": "texte", "detail": "full", "issues": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• find_opportunities≈ 936 tokens

  Turn Search Console, GA4 or Ahrefs rows (also rows the user pastes) into the fastest wins, instead of judging them by hand; content_decay and traffic_drop take search_type for Discover, News, Image or Video rows. Pick with mode: ctr_gaps = Page 1 results with a click-through rate far below normal. Needs rows[{position, page, query, clicks, impressions, ctr}]. striking_distance = Queries at positions 8 to 20 worth a push. Needs rows[{position, page, query, clicks, impressions, ctr}]. content_decay = Pages slowly losing clicks over months: a refresh queue. Needs rows[{url, month, clicks}]. traffic_drop = Explain a drop page by page, by device and country. Needs rows[{url, before, after, query, device, country}]. prune = Keep, refresh, merge (301), noindex or remove (410) per page. Needs rows[{url, clicks, impressions, conversions, referring_domains, inlinks}]. discover = Readiness for Google Discover and News, with Discover or News rows. paid_organic = Google Ads terms against Search Console: ad spend you can test cutting, content to write. Needs ads[{term, cost, clicks, conversions}], gsc[{query, position, clicks, page}]. anomalies = Spike and drop days in daily rows, with Google updates near them. Needs rows[{date, clicks, impressions, page}]. ai_queries = Question and prompt-style queries per page, for AI answers. Needs rows[{query, page, clicks, impressions, position}].

  Paramètres, retour & exemple (11)

  Paramètres

  • ads · array · optionnel
    Google Ads search terms.
  • gsc · array · optionnel
    Search Console queries.
  • mode · string · optionnel · ctr_gaps | striking_distance | content_decay | traffic_drop | prune | discover | paid_organic | anomalies
    Default ctr_gaps.
  • rows · array · optionnel
    Search Console rows for one period (28 days works well).
  • urls · array · optionnel
    Article pages to check.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • drop_date · string · optionnel
    Optional first day of the drop, YYYY-MM-DD, to check Google updates around it.
  • fix_log_id · string · optionnel
    Optional fix log from log_fix, to spot undone fixes on losing pages.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • brand_terms · array · optionnel
    Optional brand names, handled apart.
  • search_type · string · optionnel · web | discover | news | image | video
    Search Console search type of the rows, default web.

  Exemple d'appel

  {"name": "find_opportunities", "arguments": {"ads": [], "gsc": [], "mode": "ctr_gaps", "rows": [], "urls": [], "detail": "full"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• fix_log≈ 739 tokens

  Record shipped fixes, keep them live and report on them. Pick with mode: log = Record a shipped fix; checked every 6 hours, restore code on regression. Needs fixes[{url, field, new, old, via, ref}]. report = Every fix with status and results: a monthly client report. Needs fix_log_id.

  Paramètres, retour & exemple (11)

  Paramètres

  • mode · string · optionnel · log | report
    Default log.
  • brand · string · optionnel
    For the report: your agency name for the header.
  • fixes · array · optionnel
  • month · string · optionnel
    For the report: YYYY-MM.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • format · string · optionnel · status | report | annotations
    status (default), a client report, or GA4 annotations (one per ship date) for the Admin API.
  • verify · boolean · optionnel
    Check the live pages now (4 pages per call).
  • webhook · string · optionnel
    Optional https URL (Slack, Discord, Zapier, n8n, a GitHub Action) that gets the restore code when a fix is undone.
  • fix_log_id · string · optionnel
    Add to an existing log.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • shipped_at · string · optionnel
    Date the fixes went live, YYYY-MM-DD.

  Exemple d'appel

  {"name": "fix_log", "arguments": {"mode": "log", "brand": "texte", "fixes": [], "month": "texte", "detail": "full", "format": "status"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_fix_pack≈ 756 tokens

  Fixes ready to ship: as code, for a CMS through its MCP, as a pull request or at the edge. Pick with mode: fixes = Title, description, canonical, social tags, JSON-LD; platform html, wordpress, shopify, webflow, wix, storyblok, sanity, contentful, strapi, ghost, magento, git or cloudflare. Needs url. alt_texts = Write and ship missing alt texts. Needs url. web_vitals = Speed fixes as tags, WordPress steps or a Worker. Needs url. wordpress = Send fixes, new drafts and post updates to the OnPage.dev WordPress plugin for one-click approval and undo. Needs site_key.

  Paramètres, retour & exemple (12)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • alts · array · optionnel
    Step 2: the alt text per image src.
  • mode · string · optionnel · fixes | alt_texts | web_vitals | wordpress
    Default fixes.
  • note · string · optionnel
    Optional reason shown to the site owner.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • changes · array · optionnel
    Optional field and new value pairs.
  • failing · array · optionnel
    Metrics that fail for real users, if known.
  • platform · string · optionnel · html | wordpress | git | cloudflare | webflow | wix | shopify | storyblok
    html (default) for code to paste; wordpress, webflow, wix, shopify, storyblok, sanity, contentful, strapi, ghost or magento for a plan with the exact fields and
  • site_key · string · optionnel
    The site key from the plugin, wpk_...
  • change_id · string · optionnel
    Status of an earlier send.
  • framework · string · optionnel · auto | nextjs-app | nextjs-pages | nuxt | sveltekit | astro | angular | react
    With platform git: the site's framework.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "get_fix_pack", "arguments": {"url": "texte", "alts": [], "mode": "fixes", "note": "texte", "detail": "full", "changes": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• internal_links≈ 450 tokens

  Internal links and link equity. Pick with mode: suggest = Links to add, with anchors, applied by Worker or CMS. Needs audit_id. equity = Internal PageRank and click depth from a site audit. Needs audit_id.

  Paramètres, retour & exemple (9)

  Paramètres

  • mode · string · optionnel · suggest | equity
    Default suggest.
  • topic · string · optionnel
    Topic or main keyword of the target page.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • phrases · array · optionnel
    Optional: phrases to turn into the link, besides the anchor text, for example natural variants.
  • audit_id · string · optionnel
    Id of a completed site audit.
  • platform · string · optionnel · cloudflare | wordpress | git
    Optional: also return the links ready to apply: a Cloudflare Worker that links the first mention on each page, a WordPress edit plan, or the edits for the code.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • target_url · string · optionnel
    Page that should receive links.
  • important_urls · array · optionnel
    Optional. Pages that matter most, for example top pages by clicks or revenue.

  Exemple d'appel

  {"name": "internal_links", "arguments": {"mode": "suggest", "topic": "texte", "detail": "full", "phrases": [], "audit_id": "texte", "platform": "cloudflare"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• layout≈ 356 tokens

  What visitors and crawlers see on every screen size. Pick with mode: render = First screen on phone, tablet and desktop in a real browser, and what crawlers without JavaScript get (default). Needs url. probe = A measurement script to run in the user's own browser tool. analyze = Analyse the results of that script. Needs url, results.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • mode · string · optionnel · render | probe | analyze
    Default render.
  • no_js · object · optionnel
    Optional: the probe result with JavaScript turned off, for an exact comparison.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • results · array · optionnel
    One probe result per viewport, each with device set to phone, tablet or desktop.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "layout", "arguments": {"url": "texte", "mode": "render", "no_js": {}, "detail": "full", "results": [], "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• llms_txt≈ 260 tokens

  The llms.txt file for AI assistants. Pick with mode: generate = Write one from the sitemap and home page. Needs url. validate = Check an existing one and its links. Needs url.

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · optionnel
    Home page of the site, for example https://example.com.
  • mode · string · optionnel · generate | validate
    Default generate.
  • text · string · optionnel
    Optional llms.txt content to validate instead of the live file.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "llms_txt", "arguments": {"url": "texte", "mode": "generate", "text": "texte", "detail": "full", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• local≈ 959 tokens

  Local search: the site, the Business Profile and the map. Pick with mode: check = LocalBusiness markup, NAP, locations and the Business Profile (default). Needs url. reviews = Reply drafts for Google reviews, unhappy ones first, for the user's GBP connector after approval. Needs reviews[{rating, author, text, date, replied, review_id}]. demand = Business Profile search terms and geo-grid ranks into new service and location pages.

  Paramètres, retour & exemple (12)

  Paramètres

  • url · string · optionnel
    The home page, a location page or the locations overview page.
  • city · string · optionnel
    Main city, left out when matching terms to pages.
  • grid · array · optionnel
    Optional geo-grid rankings.
  • mode · string · optionnel · check | reviews | demand
    Default check.
  • pages · array · optionnel
    The site's page URLs, e.g.
  • terms · array · optionnel
    Search terms from the Business Profile performance report.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • contact · string · optionnel
    Where unhappy customers can reach you, e.g.
  • reviews · array · optionnel
  • business · string · optionnel
    Business name to sign with.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • gbp_profile · object · optionnel
    Optional: the Google Business Profile of this location, from the user's GBP connector or typed by the user, to compare with the site.

  Exemple d'appel

  {"name": "local", "arguments": {"url": "texte", "city": "texte", "grid": [], "mode": "check", "pages": [], "terms": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• measure≈ 710 tokens

  Prove and measure with numbers from the user's Search Console, GA4, Ahrefs or Semrush, including numbers the user pastes. Use it instead of calculating by hand: it handles spelling variants, control groups and trends. Pick with mode: impact = Before and after fixes, against pages you did not touch. Needs pages[{url, before, after, changed, fix}]. ai_citations = AI citations before and after, per engine. Needs pages[{url, before, after, changed}]. ai_referrals = Visits from ChatGPT, Perplexity, Gemini and other assistants, from GA4. Needs rows[{source, sessions, landing_page, period, conversions, revenue}]. brand_split = Brand versus non-brand clicks and how each moved. Needs brand_terms, rows[{query, keyword, clicks, traffic, impressions, position}]. share_of_voice = Share of the clicks against competitors from rank rows. Needs your_domain, rows[{keyword, position, volume, domain, url, group}].

  Paramètres, retour & exemple (13)

  Paramètres

  • days · integer · optionnel
    Length of each period in days.
  • mode · string · optionnel · impact | ai_citations | ai_referrals | brand_split | share_of_voice
    Default impact.
  • rows · array · optionnel
  • pages · array · optionnel
  • detail · string · optionnel · full | brief
    brief = short summary.
  • source · string · optionnel
    Where the counts come from, for example Ahrefs Brand Radar.
  • fix_date · string · optionnel
    Date the fixes went live, YYYY-MM-DD.
  • watch_ids · array · optionnel
    Optional watch ids, to list what changed on each page and when.
  • fix_log_id · string · optionnel
    Optional fix log from log_fix: takes the fix date from it and saves the result per fix, with a rollback plan for fixes that did worse.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • brand_terms · array · optionnel
    Brand and product names, and misspellings.
  • rows_before · array · optionnel
    Optional same rows from an earlier period.
  • your_domain · string · optionnel
    Your domain, e.g. example.com.

  Exemple d'appel

  {"name": "measure", "arguments": {"days": 1, "mode": "impact", "rows": [], "pages": [], "detail": "full", "source": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• plan≈ 835 tokens

  Plans for migrations, experiments and the team. Pick with mode: redirects = Redirect map for a migration or URL change. split_test = SEO split test on a page template, with the Worker. Needs urls, field, pattern. sprint = Fixes into a week plan of tickets per role. Needs fixes[{title, url, detail, severity, impact, effort}].

  Paramètres, retour & exemple (16)

  Paramètres

  • mode · string · optionnel · redirects | split_test | sprint
    Default redirects.
  • urls · array · optionnel
    Pages of one template.
  • field · string · optionnel · title | description
    What to change.
  • fixes · array · optionnel
  • hours · object · optionnel
    Hours per week per role, default 8 each.
  • weeks · number · optionnel
    Weeks to plan, default 4.
  • clicks · array · optionnel
    Optional clicks per page for a balanced split.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • format · string · optionnel · redirects | nginx | apache | nextjs | csv
    Output format, default redirects (Cloudflare Pages and Netlify).
  • pattern · string · optionnel
    The new value with {title} or {description} as placeholders.
  • new_site · string · optionnel
    New site address, to read its sitemap instead of new_urls.
  • new_urls · array · optionnel
  • old_site · string · optionnel
    Old site address, to read its sitemap instead of old_urls.
  • old_urls · array · optionnel
  • memory_key · string · optionnel
    site_memory key, records this call.
  • start_date · string · optionnel
    Optional planned start, YYYY-MM-DD.

  Exemple d'appel

  {"name": "plan", "arguments": {"mode": "redirects", "urls": [], "field": "title", "fixes": [], "hours": {}, "weeks": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• prioritize_fixes≈ 788 tokens

  Use when Search Console, GA4, Ahrefs or Semrush data is available, also to explain a traffic drop (pass clicks_previous): ranks the fixes by the traffic or revenue they can win. Rank SEO fixes by how much traffic they can win, using data from the user's other connected tools. With GA4, also pass each page's organic conversions (key events) or revenue, and fixes are ranked by the money they can bring instead of clicks.

  Paramètres, retour & exemple (6)

  Paramètres

  • pages · array · requis
  • detail · string · optionnel · full | brief
    brief = short summary.
  • source · string · optionnel · gsc | ga4 | ahrefs | semrush | other
    Where the numbers come from.
  • audit_id · string · optionnel
    Optional id of a finished site audit, so pages are not scanned again.
  • currency · string · optionnel
    Currency of revenue, for example EUR or USD.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "prioritize_fixes", "arguments": {"pages": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "revenue", "status": "partial", "actions": []}}

• request_recrawl≈ 304 tokens

  Get changed pages recrawled. Pick with mode: recrawl = Check pages are indexable, sitemap lastmod entries, IndexNow and Search Console steps (default). Needs urls. indexnow = Submit URLs to IndexNow, or set up the key. Needs urls.

  Paramètres, retour & exemple (6)

  Paramètres

  • key · string · optionnel
    The site's IndexNow key (8 to 128 letters, digits or dashes).
  • mode · string · optionnel · recrawl | indexnow
    Default recrawl.
  • urls · array · optionnel
    Changed pages on one site.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • indexnow_key · string · optionnel
    Optional IndexNow key that is live at /<key>.txt.

  Exemple d'appel

  {"name": "request_recrawl", "arguments": {"key": "texte", "mode": "recrawl", "urls": [], "detail": "full", "memory_key": "texte", "indexnow_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• robots_txt≈ 357 tokens

  robots.txt for search and AI crawlers. Pick with mode: test = Which crawlers may fetch a URL, and the rule that decides. Needs url. ai_policy = Rules per AI crawler: allow AI search, block training. Needs url, policy.

  Paramètres, retour & exemple (7)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • mode · string · optionnel · test | ai_policy
    Default test.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • policy · string · optionnel · allow_all | search_only | block_training | block_all
    Which AI crawlers to allow.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • robots_txt · string · optionnel
    Optional robots.txt content to test instead of the live file.
  • user_agents · array · optionnel
    Crawler names, for example Googlebot, GPTBot, ClaudeBot, PerplexityBot.

  Exemple d'appel

  {"name": "robots_txt", "arguments": {"url": "texte", "mode": "test", "detail": "full", "policy": "allow_all", "memory_key": "texte", "robots_txt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• scan_page≈ 370 tokens

  Scan a page for Google and AI search: 0-100 score, issues to fix first with why and how, AI readiness and key facts. Pick with mode: page = A live page by url (default). Needs url. html = Unpublished HTML before deploy, to gate a release. Needs html. deep = Everything measured on one page, by section. Needs url. rescan = Scan again after fixes and compare with the last scan. Needs url.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • html · string · optionnel
    The complete HTML document, up to 900 KB.
  • mode · string · optionnel · page | html | deep | rescan
    Default page.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • sections · array · optionnel
    Sections to include. Default: all.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "scan_page", "arguments": {"url": "texte", "html": "texte", "mode": "page", "detail": "full", "sections": [], "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• schema≈ 406 tokens

  JSON-LD structured data for rich results. Pick with mode: generate = Write JSON-LD for a page: type Article, Product, FAQPage, Organization, BreadcrumbList, VideoObject, Event, Recipe, JobPosting, SoftwareApplication, ProfilePage or Course. Needs url. validate = Validate JSON-LD for rich results. Needs jsonld. product_page = Check an existing ecommerce product page (price, stock, merchant listing fields). To write Product JSON-LD use generate with type Product. Needs url.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • mode · string · optionnel · generate | validate | product_page
    Default generate.
  • type · string · optionnel · auto | Article | Product | FAQPage | Organization | BreadcrumbList | VideoObject | Event
    Schema type, default auto.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • jsonld · string · optionnel
    The JSON-LD as text, with or without the <script> tag.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "schema", "arguments": {"url": "texte", "mode": "generate", "type": "auto", "detail": "full", "jsonld": "texte", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• share≈ 300 tokens

  Send results where the team works. Pick with mode: link = A link to the visual report. Needs url. export = A Google Sheet, CSV, Slack message or one task per issue.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    Full address, for example https://example.com/pricing.
  • mode · string · optionnel · link | export
    Default link.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • audit_id · string · optionnel
    A finished site audit from start_site_audit, to export the whole site.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • slack_webhook_url · string · optionnel
    Optional https incoming webhook (Slack, Discord, Teams) to post the summary to.

  Exemple d'appel

  {"name": "share", "arguments": {"url": "texte", "mode": "link", "detail": "full", "audit_id": "texte", "memory_key": "texte", "slack_webhook_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• site_audit≈ 918 tokens

  Audit a whole site, step by step, and work with the result. Pick with mode: start = Start an audit of up to 25 pages; returns audit_id. Needs url. continue = Scan the next pages; call until complete. Issues by code, sections, average score. Needs audit_id. import = Turn a crawl from Screaming Frog, Ahrefs or Semrush (up to 500 pages) into an audit_id. Needs pages[{url, status, redirect_to, title, meta_description, h1}]. compare = What changed since the last audit, or against a competitor audit. Needs audit_id. report = A client-ready report page with a link. Needs audit_id.

  Paramètres, retour & exemple (13)

  Paramètres

  • url · string · optionnel
    Full address, for example https://example.com.
  • mode · string · optionnel · start | continue | import | compare | report
    Default start.
  • note · string · optionnel
    Optional short note for the reader, shown at the top.
  • brand · string · optionnel
    Optional agency or team name to show instead of OnPage.dev.
  • links · array · optionnel
    Optional internal links, for link equity, orphans and internal link suggestions.
  • pages · array · optionnel
    One row per crawled page.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • source · string · optionnel
    Where the rows come from, for example Screaming Frog or Ahrefs Site Audit.
  • audit_id · string · optionnel
    The id returned by start_site_audit.
  • max_pages · integer · optionnel
    How many pages to audit, default 10, at most 25.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • previous_audit_id · string · optionnel
    Optional: the audit to compare with.
  • competitor_audit_id · string · optionnel
    Optional: a finished audit of a competitor's site, to compare the two sites side by side instead of over time.

  Exemple d'appel

  {"name": "site_audit", "arguments": {"url": "texte", "mode": "start", "note": "texte", "brand": "texte", "links": [], "pages": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• site_memory≈ 412 tokens

  A memory per site that every OnPage.dev tool writes to, across chats and clients. Open it first when working on a site over time. Pick with mode: open = Open or create the memory, bind it to this chat, get the brief and next steps (default). Needs url. next = The best next steps from everything recorded. timeline = What happened, newest first. note = Record a decision or context. Needs note. forget = Delete the memory (ask the user first). Needs memory_key.

  Paramètres, retour & exemple (8)

  Paramètres

  • url · string · optionnel
    The site's home page.
  • kind · string · optionnel · scan | audit | fix | measure | rank | alert | plan | content
  • mode · string · optionnel · open | next | timeline | note | forget
    Default open.
  • note · string · optionnel
  • limit · number · optionnel
  • detail · string · optionnel · full | brief
    brief = short summary.
  • memory_key · string · optionnel
    The memory_key you got when the memory was created.
  • share_learning · boolean · optionnel
    Opt in (true) or out (false) of sharing anonymous results: only the fix type and the rounded lift, never the site, URLs or numbers.

  Exemple d'appel

  {"name": "site_memory", "arguments": {"url": "texte", "kind": "scan", "mode": "open", "note": "texte", "limit": 1, "detail": "full"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• sitemap≈ 245 tokens

  The XML sitemap. Pick with mode: check = Check the sitemap and a sample of its URLs. Needs url. generate = Write a sitemap from a page list or audit. Needs audit_id.

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · optionnel
    The site's home page, or the sitemap URL itself.
  • mode · string · optionnel · check | generate
    Default check.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • audit_id · string · optionnel
    A finished site audit.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "sitemap", "arguments": {"url": "texte", "mode": "check", "detail": "full", "audit_id": "texte", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• snippet≈ 325 tokens

  How a page looks in Google and when shared, measured in pixels the way Google truncates. Use it instead of estimating title or description length. Pick with mode: search = Title and description as Google shows them; give title (and description) or a url to read them. social = Open Graph and X cards, and the share image. Needs url.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    Page to read the current title and description from, when no title is given.
  • mode · string · optionnel · search | social
    Default search.
  • title · string · optionnel
    Proposed title tag text.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • description · string · optionnel
    Proposed meta description.

  Exemple d'appel

  {"name": "snippet", "arguments": {"url": "texte", "mode": "search", "title": "texte", "detail": "full", "memory_key": "texte", "description": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• technical≈ 596 tokens

  Technical checks across pages and logs. Pick with mode: hreflang = Hreflang across language versions, with the corrected tag set. Needs url. parameters = URL parameters and filters that waste crawl budget. duplicates = Duplicate and near-duplicate pages. Needs audit_id. extract = One value pulled from many pages. Needs urls. logs = Access logs: what Googlebot and AI crawlers really crawl, with IP verification. Needs log.

  Paramètres, retour & exemple (12)

  Paramètres

  • log · string · optionnel
    Raw access log lines, one request per line.
  • url · string · optionnel
    Full address of one language version of the page.
  • mode · string · optionnel · hreflang | parameters | duplicates | extract | logs
    Default hreflang.
  • urls · array · optionnel
    Optional extra URLs, for example from server logs or Search Console.
  • regex · string · optionnel
    A regular expression; the first group is returned if there is one, otherwise the whole match.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • jsonld · string · optionnel
    A JSON-LD path: the @type, then the properties, for example Product.offers.price or Article.author.name.
  • audit_id · string · optionnel
    Id of a completed site audit.
  • selector · string · optionnel
    CSS selector, for example .price, h1 or link[rel=canonical].
  • attribute · string · optionnel
    With selector: read this attribute instead of the text, for example href or content.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • sitemap_urls · array · optionnel
    Optional: the URLs from the site's sitemap, to find pages bots never crawl.

  Exemple d'appel

  {"name": "technical", "arguments": {"log": "texte", "url": "texte", "mode": "hreflang", "urls": [], "regex": "texte", "detail": "full"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• text_quality≈ 294 tokens

  Readability and correct language. Pick with mode: readability = Readability that fits the page and the pages that rank. Needs url. spelling = Spelling and grammar errors in about 30 languages. Needs url.

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    Your page.
  • mode · string · optionnel · readability | spelling
    Default readability.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • keyword · string · optionnel
    Optional: the search term, for context.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • competitors · array · optionnel
    Optional: top organic results for the keyword.

  Exemple d'appel

  {"name": "text_quality", "arguments": {"url": "texte", "mode": "readability", "detail": "full", "keyword": "texte", "memory_key": "texte", "competitors": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• track_rankings≈ 885 tokens

  Use for ongoing rank tracking without picking keywords by hand. Each run, fetch Search Console rows by query and page (last 7 or 28 days) and, if connected, the rows of Ahrefs Rank Tracker (rank-tracker-overview) or Semrush Position Tracking, plus GA4 conversions or revenue per landing page if available, and pass them with the tracker_id (leave it out on the first run to create a tracker).

  Paramètres, retour & exemple (11)

  Paramètres

  • site · string · optionnel
    Your site. Needed on the first run.
  • action · string · optionnel · run | status | stop
    run (default), status or stop.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • gsc_rows · array · optionnel
    Search Console rows by query and page for the period.
  • fix_log_id · string · optionnel
    Optional fix log (log_fix) whose pages count as work done.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • tracker_id · string · optionnel
    From the first run. Leave out to create a tracker.
  • conversions · array · optionnel
    Optional GA4 key events or revenue per landing page.
  • webhook_url · string · optionnel
    Optional https webhook for the changes (Slack and Discord work).
  • tracker_rows · array · optionnel
    Ahrefs Rank Tracker or Semrush Position Tracking rows.
  • money_keywords · array · optionnel
    Optional keywords you always want followed.

  Exemple d'appel

  {"name": "track_rankings", "arguments": {"site": "texte", "action": "run", "detail": "full", "gsc_rows": [], "fix_log_id": "texte", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"runs": 1, "events": [], "groups": {}, "trackerId": "texte"}}

• tracking≈ 428 tokens

  Whether analytics and consent are set up right, and whether the numbers add up. Pick with mode: ga4 = GA4 tags, events and duplicates. Needs url. consent = Cookie banner and Consent Mode v2. Needs url. gsc_vs_ga4 = Search Console clicks against GA4 sessions per page: broken or filtered tracking. Needs gsc[{page, clicks}], ga4[{landing_page, sessions}].

  Paramètres, retour & exemple (6)

  Paramètres

  • ga4 · array · optionnel
    GA4 sessions per landing page, organic Google only.
  • gsc · array · optionnel
    Search Console clicks per page.
  • url · string · optionnel
    Full address of the page, for example https://example.com/.
  • mode · string · optionnel · ga4 | consent | gsc_vs_ga4
    Default ga4.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • memory_key · string · optionnel
    site_memory key, records this call.

  Exemple d'appel

  {"name": "tracking", "arguments": {"ga4": [], "gsc": [], "url": "texte", "mode": "ga4", "detail": "full", "memory_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• watch≈ 701 tokens

  Monitoring that runs on its own and posts changes to a webhook. Each kind takes action create (default), status or stop where it applies. Pick with mode: page = Watch one page (or a competitor page with competitor_of) for SEO changes. Needs url. page_status = Latest result of a page watch. Needs watch_id. page_stop = Stop a page watch. Needs watch_id. site_audit = Audit the whole site every 1, 7 or 30 days and alert on regressions. guard = Every 6 hours: robots.txt, sitemap, https, noindex and canonical on key pages, for deploy accidents. competitors = Weekly new, updated and removed pages from competitors' sitemaps, flagged by your topics.

  Paramètres, retour & exemple (15)

  Paramètres

  • url · string · optionnel
    Full address, for example https://example.com/pricing.
  • mode · string · optionnel · page | page_status | page_stop | site_audit | guard | competitors
    Default page.
  • pages · array · optionnel
    Key pages to guard besides the home page (money pages first).
  • action · string · optionnel · create | status | stop
    create (default), status or stop.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • topics · array · optionnel
    Your topics or keywords, to flag overlapping pages.
  • guard_id · string · optionnel
    For status and stop.
  • watch_id · string · optionnel
    For status and stop.
  • max_pages · number · optionnel
    Pages per audit, default 25.
  • every_days · number · optionnel · 1 | 7 | 30
    How often, default 7.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • competitors · array · optionnel
    Competitor home pages.
  • schedule_id · string · optionnel
    For status and stop.
  • webhook_url · string · optionnel
    Optional https URL that receives a JSON POST when something changes, for example a Slack or Discord incoming webhook.
  • competitor_of · string · optionnel
    Optional: your own page.

  Exemple d'appel

  {"name": "watch", "arguments": {"url": "texte", "mode": "page", "pages": [], "action": "create", "detail": "full", "topics": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• web_vitals≈ 262 tokens

  Core Web Vitals from real Chrome users. Pick with mode: now = The latest field data for a page or site. Needs url. trend = Weekly history, before and after a change date. Needs url.

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · optionnel
    Full address of the page, for example https://example.com/pricing.
  • mode · string · optionnel · now | trend
    Default now.
  • detail · string · optionnel · full | brief
    brief = short summary.
  • memory_key · string · optionnel
    site_memory key, records this call.
  • change_date · string · optionnel
    Optional date a speed fix went live, YYYY-MM-DD.

  Exemple d'appel

  {"name": "web_vitals", "arguments": {"url": "texte", "mode": "now", "detail": "full", "memory_key": "texte", "change_date": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://onpage.dev/mcp