momentic MCP server
com.momenticmarketing/momenticmomenticmarketing.comstreamable-httpv0.2.0Scanned
Free SEO, GEO, and AEO audits: analyze any page or domain, AI-crawler access, agent readiness.
12 tools: 5 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 3
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the momentic MCP server can do
The momentic MCP server is published by momenticmarketing.com, a domain the MCP Registry verified. It has 12 tools. It can create or change data (5 tools: ask_momentic, check_bots, parse_freshness_signals, extract_links and 1 more), but cannot delete data. 7 tools only read.
1 tool reads private data (analyze_site); 3 tools bring in text other people can write (search, analyze_page and analyze_site); 3 tools can send data out of your system (analyze_page, check_bots and parse_freshness_signals). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 0.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
12 tools
Changes things 5Claude Code: ask
ask_momenticAsks 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
check_botsProbes a URL with AI crawler user agents, using the operators' current documented strings (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, Perplexity…Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
compute_link_graphPure graph computation over a crawled page set.No findings
Why it is in this group
- The name "compute_link_graph" says "link": a word for a change.
Description, as the server wrote it 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.
extract_linksPure HTML parser.No findings
Why it is in this group
- The name "extract_links" says "link": a word for a change.
Description, as the server wrote it 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.
parse_freshness_signalsPure parser (no fetching).Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Only reads 7Show 7 read-only tools
analyze_pageFetches any public URL and returns structured on-page SEO signals: title, meta description, canonical (+ canonicalCount), lang, heading counts, schema types (JSON-LD including @gra…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "analyze_page" says "analyze": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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.
analyze_siteProbes 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-Use…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "analyze_site" says "analyze": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it 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).
get_brand_overviewReturns the canonical AI-readable description of Momentic from /llms.txt.No findings
Why it is in this group
- The name "get_brand_overview" says "get": a word for reading.
Description, as the server wrote it Returns the canonical AI-readable description of Momentic from /llms.txt. Use for authoritative brand info, positioning, services, and contact.
get_pageFetches a Momentic page as Markdown (uses Cloudflare's Markdown for Agents).No findings
Why it is in this group
- The name "get_page" says "get": a word for reading.
Description, as the server wrote it 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.
list_pagesLists pages on momenticmarketing.com from sitemap.xml.No findings
Why it is in this group
- The name "list_pages" says "list": a word for reading.
Description, as the server wrote it 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.
lookup_entityResolves a brand/topic/person to a structured entity record built from Wikidata + Wikipedia (free APIs, no auth).No findings
Why it is in this group
- The name "lookup_entity" says "lookup": a word for reading.
Description, as the server wrote it 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.
searchFull-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 guid…Reads text others writeNo findings
Why it is in this group
- The name "search" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it 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.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
9 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__momentic__analyze_site"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:42 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://momenticmarketing.com/mcp: tools/list returned 12 tools to an anonymous client, including ask_momentic (write), check_bots (write), parse_freshness_signals (write), extract_links (write), compute_link_graph (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http momentic https://momenticmarketing.com/mcpclaude mcp add --transport http momentic https://momenticmarketing.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__momentic__get_brand_overview",
"mcp__momentic__list_pages",
"mcp__momentic__get_page",
"mcp__momentic__search",
"mcp__momentic__analyze_site",
"mcp__momentic__lookup_entity"
],
"ask": [
"mcp__momentic__ask_momentic",
"mcp__momentic__analyze_page",
"mcp__momentic__check_bots",
"mcp__momentic__parse_freshness_signals",
"mcp__momentic__extract_links",
"mcp__momentic__compute_link_graph"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as momentic. Review it before you use it.
Capability tags behind 5 rules
- mcp__momentic__search untrusted-input
- mcp__momentic__analyze_page untrusted-input, outbound
- mcp__momentic__analyze_site private-data, untrusted-input
- mcp__momentic__check_bots outbound
- mcp__momentic__parse_freshness_signals outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.momenticmarketing/momentic/verify?hash=5407a4058a87ce76ab00b29d995ac21ebb7234052e99aecb5ed87af47f1cada5" | jq -e '.changed == false'Pinned hash 5407a4058a87, from Nov 13, 2026, 19:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.momenticmarketing/momentic/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.momenticmarketing/momentic)Source: MCP Registry. Synced Oct 21, 2026, 17:59 UTC.
momentic MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the momentic MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the momentic MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the momentic MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the momentic MCP server have?
- 12 tools: 5 write, 7 read. ask_momentic, check_bots, parse_freshness_signals, extract_links, compute_link_graph, get_brand_overview, list_pages, get_page and 4 more.
Does the momentic MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the momentic MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): analyze_page, check_bots and parse_freshness_signals.
Has the momentic MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.