Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Added "ask_momentic" (11 tools before, 12 now)
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.
Changed the definition of "analyze_site", "check_bots" and "search"
⟨16 unchanged words⟩ OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User,Claude-Web,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 ⟨72 unchanged words⟩
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 ⟨89 unchanged words⟩
Changed the definition of "search"
Full-text search across every page on momenticmarketing.com (titlesblog posts,headingsresearch,bodythetextGoogleandupdateimagetracker,descriptionscase studies, Content Academy guides, Atlas, team pages). Returns up to 10matchingpages,bestrankedfirst
Changed the definition of "analyze_page", "analyze_site" and "check_bots"
⟨7 unchanged words⟩ on-page SEO signals: title, meta description, canonical (+ canonicalCount), lang, heading counts,JSON-LDschema 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 whetherCloudflaremarkdownMarkdownisforservedAgentsfor
Changed the definition of "search"
SearchesFull-text search acrossMomenticevery pageURLs fromonsitemap.xmlmomenticmarketing.com (case-insensitivetitles,substringheadings,matchbodyontextURLand image descriptions).For
Certificate recorded, valid to 2026-11-27
Authorization not required
First tool surface recorded: 11 tools (server version 0.2.0)
Showing the latest 8 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨25 unchanged words⟩ :"Optional UA strings to test. Defaults toGPTBot,theClaudeBot,botsClaude-Web,listedPerplexityBot,aboveGoogleOther,(robots.txt tokens such as Google-Extended,CCBot,and Applebot-Extended,ChatGPT-User,aremeta-externalagent.not probed).","items":{"type":"string"}, ⟨6 unchanged words⟩
⟨7 unchanged words⟩ (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 ⟨18 unchanged words⟩
⟨11 unchanged words⟩ title, type, date, author, image,passagepassage; tracker pages also tracker: status, announced, started, completed, kind).","enum":["text","json" ⟨6 unchanged words⟩ or question","type":"string"},"recent":{"description":"Optional: newest first among relevant pages (also implied by words like latest, newest, most recent in the query). Tracker pages sort by the date Google announced the update.","type":"boolean"},"type":{"description":"Optional: only pages of this ⟨8 unchanged words⟩ ","atlas","event","team","service","news","agent","page"],"type":"string"}} ⟨4 unchanged words⟩
{"additionalProperties":false,"properties":{"format":{"description":"Optional: json returns structured results (url, title, type, date, author, image, passage).","enum":["text","json"],"type":"string"},"query":{"description":"Search term or question","type":"string"},"type":{"description":"Optional: only pages of this content type.","enum":["research","blog","google-update","case-study","guide","atlas","event","team","service","page"],"type":"string"}},"required":[ ⟨3 unchanged words⟩
Probes a domain root for site-wide AI-discovery signals:/llms.txt,/llms.txt; /robots.txt(parsedAI-botperrulesRFC 9309 forGPTBot/ClaudeBot/PerplexityBot/GoogleOther/CCBot/Google-Extended/Applebot-Extended)GPTBot,/sitemap.xmlOAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, Claude-Web, PerplexityBot, Perplexity-User, GoogleOther, Google-Extended, CCBot, Applebot-Extended, Meta-ExternalAgent (URLaiBotStatuscountis+thesectionsverdict 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,/.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).
Probes a URL withmultipleAIbotcrawleruser-agentsuser agents (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User, GoogleOther, CCBot, Applebot, meta-externalagent) in parallel, plus a regular Chrome browser request as a baseline, and returns per-bot reachability (status, key WAF/CDN headers,and averdict). Reveals WAF/CDN-layer blocks that robots.txt auditsmissmiss.—Verdicts:e.g.reachable,ablocked-403,siteblocked-4xx,thatchallenged-by-cdnallows(includingGPTBot200inchallengerobots.txtpages),butrate-limited-429,returnsredirected-to-block-page,403inconclusive-not-bot-specificto(theitbrowseratbaselineCloudflare.wasVerdicts:refusedreachabletoo,blocked-403,sochallenged-by-cdn,therate-limited-429block is not aimed at the bot),server-error-5xxnot-found,redirected-to-block-pageserver-error-5xx, timeout, fetch-error.Thesummary.blockedsummary.blockingPatterncountsfieldonlynamesbot-specificexactlyblocks;whichtimeoutsbotsandgoterrorsblockedarewhencountedothersseparately.gotRequeststhrough.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.