Momentic MCP Server

Fetches any public URL and returns structured on-page SEO signals: title, meta description, canonical (+ canonicalCount), lang, heading counts, schema types (JSON-LD including @graph and nested entities, plus microdata and schema.org RDFa; schemaTypesBySyntax splits them), OpenGraph/Twitter cards (any attribute order), internal/external link counts, word count (body text without scripts, templates, comments; see wordCountMethod), and whether markdown is served for Accept: text/markdown. Text values are entity-decoded. pageLoaded:false means the checker was refused or got an error or challenge page; then title, schemaTypes and wordCount are null (unknown, not empty). markdownNegotiation is null with markdownNegotiationChecked:false when the markdown probe was refused.

Probes a domain root for site-wide AI-discovery signals: /llms.txt; /robots.txt parsed per RFC 9309 for GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User, GoogleOther, Google-Extended, CCBot, Applebot-Extended, Meta-ExternalAgent, meta-externalfetcher, Amzn-SearchBot, MistralAI-User, DuckAssistBot (aiBotStatus is the verdict for the homepage path / only; aiBotDisallows lists rules that still block an allowed bot elsewhere); the sitemap (/sitemap.xml or robots.txt Sitemap lines, sitemap indexes followed, gzip read): urlCount is unique page URLs, urlCountComplete says whether every sitemap file was read; /.well-known/agent-skills/index.json, /.well-known/api-catalog, /.well-known/mcp/server-card.json; and the homepage Link header. Every file reports found: true, false (checked and absent, including HTML catch-all pages), or null with checked:false (blocked, erroring or timed out: unknown).

Asks Ask Momentic a question and returns its answer, written by AI from momenticmarketing.com pages, with the Momentic pages it is based on as sources. Use it for questions about Momentic (services, Atlas, the team, case studies, pricing) and about SEO and AI search topics Momentic publishes research on, such as AI chatbot market share, AI Overviews, llms.txt, AI crawlers or query fan out. A question someone asked before returns at once; a new one takes about 30 seconds. If the result says the answer is still being written, call the tool again with the same question after about 30 seconds.

Probes a URL with AI crawler user agents, using the operators' current documented strings (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User, GoogleOther, Google-Agent, CCBot, Applebot, meta-externalagent, meta-externalfetcher, Amzn-SearchBot, MistralAI-User, DuckAssistBot) in parallel, plus a regular Chrome browser request as a baseline, and returns per-bot reachability (status, key WAF/CDN headers, verdict). Reveals WAF/CDN-layer blocks that robots.txt audits miss. Verdicts: reachable, blocked-403, blocked-4xx, challenged-by-cdn (including 200 challenge pages), rate-limited-429, redirected-to-block-page, inconclusive-not-bot-specific (the browser baseline was refused too, so the block is not aimed at the bot), not-found, server-error-5xx, timeout, fetch-error. summary.blocked counts only bot-specific blocks; timeouts and errors are counted separately. Requests come from Cloudflare's network, not the bot operators' IPs (see probe.note). Google-Extended and Applebot-Extended are robots.txt tokens, not user agents, and are not probed.

Returns the canonical AI-readable description of Momentic from /llms.txt. Use for authoritative brand info, positioning, services, and contact.

Pure graph computation over a crawled page set. Input: an array of {url, internalLinks: [{href, anchor}, ...], title?, bodyText?}. Returns orphan pages (in-degree 0, excluding the homepage), hubs (top-N by in-degree), authorities (top-N by out-edges to hubs), PageRank-lite ranking, anchor-diversity issues (all-anchors-same, no-descriptive-anchors), connected components, and isolated clusters. With options.findMentions=true and title+bodyText supplied, also returns mention-not-linked suggestions. URL normalization (trailing slash, lowercased host, dropped utm_*/fbclid/gclid/etc.) is on by default.

Pure HTML parser. Given a single page's HTML and its baseUrl, returns every <a href> resolved to absolute, separated into internal vs external by host, with cleaned anchor text, rel attribute, and nofollow flag. Skips fragments, mailto:, tel:, javascript:, and empty hrefs. Designed to feed compute_link_graph: the agent crawls pages on the user's machine (their IP, no Cloudflare subrequest cap) and calls extract_links per page, then ships the structured page data into compute_link_graph.

Resolves a brand/topic/person to a structured entity record built from Wikidata + Wikipedia (free APIs, no auth). Pass exactly one of: `name` (search by string), `qid` (Wikidata Q-number to skip search), or `wikipediaTitle` (resolves to QID via the article's wikibase_item). Returns: qid, label, description, instanceOf (P31 with resolved labels), sameAs (Wikipedia + claim-derived URLs for Twitter/Instagram/Facebook/GitHub/LinkedIn/YouTube/Crunchbase/official site), sitelinks (top 10 language wikis) and sitelinkCount, Wikipedia summary + thumbnail, Wikipedia section outline (canonical sub-topic structure for content briefs), and alternativeMatches when a name search returned multiple candidates. Powers entity-graph alignment checks (Stage 4 trustworthiness, Stage 10B verification) and feeds the content-brief skill's outline.

Fetches a Momentic page as Markdown (uses Cloudflare's Markdown for Agents). Pass an absolute path like "/team/jane-doe" or a full momenticmarketing.com URL.

Lists pages on momenticmarketing.com from sitemap.xml. Optional `section` filter: team, case-studies, capabilities, services, blog, seo-news, content-academy, google-updates, blog-categories, careers, about, contact, pricing.

Pure parser (no fetching). Given HTML plus optional response headers and a sitemap entry for the same URL, extracts every freshness marker on the page — HTTP Last-Modified, sitemap lastmod, JSON-LD dateModified/datePublished (including @graph), OpenGraph article:modified_time/published_time, meta updated/dc.date.modified/dcterms.modified/itemprop dateModified, and the first labelled visible date (Last updated / Updated / Published). Returns per-source ISO dates, the freshest source, cross-source agreement spread, and heuristic flags (stale year in title, suspicious future date, only-published-not-modified, none-at-all). Powers the geo-aeo-readiness skill's freshness check — `Last-Modified` headers and `dateModified` JSON-LD are weighted heavily for AI grounding eligibility.

Full-text search across every page on momenticmarketing.com (blog posts, research, the Google update tracker with each update's status and dates, case studies, Content Academy guides, Atlas, team pages, careers, the SEO news feed item by item, and Momentic's agent tools and skills), including pages published since Webflow's sitemap was last rebuilt. Returns up to 10 pages ranked by relevance (newest first when the query asks for the latest, newest or most recent; tracker pages by the date Google announced the update), each with its URL, title, content type, published date, author and the passage that best matches the query. Read a full page with get_page.