Skip to content

RankRoot: AI visibility audit MCP server

io.github.zachhhhh/rankrootzachhhhhstreamable-httpv0.1.1Scanned

Audit a site's visibility to ChatGPT, Perplexity, Claude and AI agents. Generates llms.txt.

16 tools: 11 change things and 5 only read.

Tools: 0 delete, 0 irreversible, 11 write, 5 read.
  • Reads private data · 1
  • Reads text others write · 12
  • Can send data out · 11
  • 3 findings

Tools listed without sign-in. Remote posture

With Anlyon

11 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.
Govern this server →

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 RankRoot: AI visibility audit MCP server can do

The RankRoot: AI visibility audit MCP server is published by the GitHub account zachhhhh. It has 16 tools. It can create or change data (11 tools: audit_ai_visibility, audit_seo, check_core_web_vitals, generate_ai_visibility_files and 7 more), but cannot delete data. 5 tools only read.

1 tool reads private data (amplify_preview); 12 tools bring in text other people can write (audit_ai_visibility, audit_seo, check_core_web_vitals and 9 more); 11 tools can send data out of your system (audit_ai_visibility, audit_seo, check_core_web_vitals and 8 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 0.1.1.

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.

16 tools

Changes things 11Claude Code: ask
  • amplify_create_campaignTurn one page (url) or text into a native post for every enabled channel in every chosen language, saved as drafts.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "amplify_create_campaign" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Turn one page (url) or text into a native post for every enabled channel in every chosen language, saved as drafts. Nothing is published. Use dry_run to see posts without saving, and idempotency_key so a retry never makes a duplicate. Needs the customer's key.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • amplify_edit_postChange a draft's text, thread or title.Can send data outNo findings

    Why it is in this group

    • The name "amplify_edit_post" says "edit": a word for a change.

    What it can reach

    • outboundThe name "amplify_edit_post" says "edit" and "post": it writes something other people read.
    Description, as the server wrote it
    Change a draft's text, thread or title. The platform checks (length, hashtags, hype words, required settings) run again and come back as warnings.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • amplify_list_postsPosts newest first, with status (draft, scheduled, published, failed, rejected), schedule time, live URL, warnings, claims to confirm and engagement metrics.Reads text others write1 finding

    Why it is in this group

    • The name "amplify_list_posts" says "list": a word for reading.
    • The description's first verb is "post": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe name "amplify_list_posts" says "list" and "post": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "post" and "url": it reads web pages, which anyone can write.

    Findings

    • Warn

      The server marks "amplify_list_posts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "amplify_list_posts" says "list": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Posts newest first, with status (draft, scheduled, published, failed, rejected), schedule time, live URL, warnings, claims to confirm and engagement metrics.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • amplify_previewWrite native posts for X, LinkedIn and Threads from any public page, in up to 3 languages, so the user can see what RankRoot Amplify would publish.Reads private dataReads text others writeCan send data out1 finding

    Why it is in this group

    • The name "amplify_preview" says "preview": a word for reading.
    • The description's first verb is "write": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • private-dataThe description's first sentence says "thread": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "write" and "post": it reads posts, which other people 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.

    Findings

    • Warn

      The server marks "amplify_preview" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "amplify_preview" says "preview": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Write native posts for X, LinkedIn and Threads from any public page, in up to 3 languages, so the user can see what RankRoot Amplify would publish. Free, no key. Nothing is stored or posted.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • amplify_schedule_postsSchedule draft posts in the customer's Postiz at the next good local time for each platform and language (or at `at`), within the per-channel daily cap and spacing.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "amplify_schedule_posts" says "schedule": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "amplify_schedule_posts" says "schedule" and "post": it writes something other people read.
    Description, as the server wrote it
    Schedule draft posts in the customer's Postiz at the next good local time for each platform and language (or at `at`), within the per-channel daily cap and spacing. Only works if the customer allowed agents to schedule; posts with claims to confirm or warnings are skipped for the owner to review. Returns what was scheduled and why anything was skipped.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • audit_ai_visibilityScore how discoverable a website is by AI answer engines (ChatGPT, Perplexity, Claude, Google AI Overviews) and AI agents.Reads text others writeCan 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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Score how discoverable a website is by AI answer engines (ChatGPT, Perplexity, Claude, Google AI Overviews) and AI agents. Returns a 0-100 score, per-category scores and a prioritized fix list.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • audit_seoClassic SEO audit of a page, weighted like a full SEO audit: technical (canonical, indexability, redirects, HTTPS/HSTS, security headers, mobile viewport, hreflang, 2 MB HTML limit…Reads text others writeCan 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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Classic SEO audit of a page, weighted like a full SEO audit: technical (canonical, indexability, redirects, HTTPS/HSTS, security headers, mobile viewport, hreflang, 2 MB HTML limit, back-button hijacking), content and E-E-A-T trust signals, on-page (title, meta description, headings, internal links, anchor text), schema validation (parse errors, required properties, retired rich-result types), performance, images and AI search readiness. Returns a 0-100 score and prioritized issues with fixes.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • check_ai_crawler_accessCheck which AI crawlers (OAI-SearchBot, ChatGPT-User, GPTBot, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended and more) a site's robots.txt and firewall/CDN let in.Reads text others writeCan 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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Check which AI crawlers (OAI-SearchBot, ChatGPT-User, GPTBot, ClaudeBot, Claude-SearchBot, PerplexityBot, Google-Extended and more) a site's robots.txt and firewall/CDN let in. Flags blocked AI search bots, which cost citations.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • check_core_web_vitalsLCP, INP and CLS for a URL from Google PageSpeed Insights (mobile): Chrome UX Report field data (75th percentile, 28 days) when Google has it, plus Lighthouse lab metrics and the b…Reads text others writeCan 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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    LCP, INP and CLS for a URL from Google PageSpeed Insights (mobile): Chrome UX Report field data (75th percentile, 28 days) when Google has it, plus Lighthouse lab metrics and the biggest speed opportunities. Takes up to a minute.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • generate_ai_visibility_filesGenerate ready-to-publish llms.txt, an AI-bot-friendly robots.txt and schema.org JSON-LD for a website, based on its current homepage.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "generate_ai_visibility_files" says "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Warn

      The server marks "generate_ai_visibility_files" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "generate_ai_visibility_files" says "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Generate ready-to-publish llms.txt, an AI-bot-friendly robots.txt and schema.org JSON-LD for a website, based on its current homepage.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • submit_launchLaunch the user's product on RankRoot for free: a public launch page, a listing in the launch directory and the product's category, and a count of visitors sent.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "submit_launch" says "submit": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Launch the user's product on RankRoot for free: a public launch page, a listing in the launch directory and the product's category, and a count of visitors sent. Free launches go live in about a week after the user confirms by email. With a Launch Kit license key (key) it goes live today and is featured for 30 days. Ask the user before submitting: it publishes their product publicly.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 5Show 5 read-only tools
  • amplify_statusConnected channels, languages, mode, guardrails, post counts and what has performed best for this customer.Reads text others writeNo findings

    Why it is in this group

    • The name "amplify_status" says "status": 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
    Connected channels, languages, mode, guardrails, post counts and what has performed best for this customer. Needs the customer's Growth Employee key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_pricingList RankRoot plans (free scan, Launch Kit one-time, Growth Tracker monthly or yearly, done-for-you Growth Employee monthly or yearly) with prices, limits, checkout links and which…No findings

    Why it is in this group

    • The name "get_pricing" says "get": a word for reading.
    Description, as the server wrote it
    List RankRoot plans (free scan, Launch Kit one-time, Growth Tracker monthly or yearly, done-for-you Growth Employee monthly or yearly) with prices, limits, checkout links and which plan fits which user. Agents with a USDC wallet can pay directly over x402: GET https://getrankroot.com/api/agent/check?url= ($0.50) or POST https://getrankroot.com/api/agent/employee {website} ($149, 30 days, key returned at once). Otherwise give the user the checkout link.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_launchesFind software products for a need: new SaaS, AI tools and apps launched on RankRoot, each with a fact-checked profile (what it does, who it's for, pricing when published).No findings

    Why it is in this group

    • The name "list_launches" says "list": a word for reading.
    Description, as the server wrote it
    Find software products for a need: new SaaS, AI tools and apps launched on RankRoot, each with a fact-checked profile (what it does, who it's for, pricing when published). Pass the user's need as query ("invoicing for freelancers", "uptime monitoring"). Featured products are paid placements and are marked. Optional category: an industry slug such as sales-crm or product-analytics.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • validate_llms_txtFetch a site's llms.txt (pass the site URL, or a URL ending in /llms.txt or /llms-full.txt for a subpath file) and check it against the llmstxt.org format: H1, summary, H2 link lis…Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "validate_llms_txt" says "validate": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • 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
    Fetch a site's llms.txt (pass the site URL, or a URL ending in /llms.txt or /llms-full.txt for a subpath file) and check it against the llmstxt.org format: H1, summary, H2 link lists, Optional section.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

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.

132 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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__rankroot__amplify_preview"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:13 UTC, unchanged since Oct 29, 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
11
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 11 tools that change things (11 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://getrankroot.com/api/mcp: tools/list returned 16 tools to an anonymous client, including audit_ai_visibility (write), audit_seo (write), check_core_web_vitals (write), generate_ai_visibility_files (write), check_ai_crawler_access (write) and 6 more

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 8 to 11

Findings

Matches of fixed checks, with the text they matched.

3 warn
  • The server marks "generate_ai_visibility_files" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "generate_ai_visibility_files" says "generate": a word for a change.

    What this check looks for
  • The server marks "amplify_preview" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "amplify_preview" says "preview": a word for reading.

    What this check looks for
  • The server marks "amplify_list_posts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "amplify_list_posts" says "list": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools4 changed.~4 changedView diff
  2. Tools10 added, 2 changed.+10 added~2 changedView diff
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 8 -> 11.View diff
    • Tools that change things, listed without credentials: 8 to 11

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http rankroot https://getrankroot.com/api/mcp
claude mcp add --transport http rankroot https://getrankroot.com/api/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__rankroot__get_pricing",
      "mcp__rankroot__get_checkout_link",
      "mcp__rankroot__list_launches",
      "mcp__rankroot__amplify_status"
    ],
    "ask": [
      "mcp__rankroot__audit_ai_visibility",
      "mcp__rankroot__audit_seo",
      "mcp__rankroot__check_core_web_vitals",
      "mcp__rankroot__generate_ai_visibility_files",
      "mcp__rankroot__check_ai_crawler_access",
      "mcp__rankroot__validate_llms_txt",
      "mcp__rankroot__submit_launch",
      "mcp__rankroot__amplify_preview",
      "mcp__rankroot__amplify_create_campaign",
      "mcp__rankroot__amplify_list_posts",
      "mcp__rankroot__amplify_edit_post",
      "mcp__rankroot__amplify_schedule_posts"
    ],
    "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 rankroot. Review it before you use it.

Capability tags behind 13 rules
  • mcp__rankroot__audit_ai_visibility untrusted-input, outbound
  • mcp__rankroot__audit_seo untrusted-input, outbound
  • mcp__rankroot__check_core_web_vitals untrusted-input, outbound
  • mcp__rankroot__generate_ai_visibility_files untrusted-input, outbound
  • mcp__rankroot__check_ai_crawler_access untrusted-input, outbound
  • mcp__rankroot__validate_llms_txt untrusted-input, outbound
  • mcp__rankroot__submit_launch untrusted-input, outbound
  • mcp__rankroot__amplify_preview private-data, untrusted-input, outbound
  • mcp__rankroot__amplify_status untrusted-input
  • mcp__rankroot__amplify_create_campaign untrusted-input, outbound
  • mcp__rankroot__amplify_list_posts untrusted-input
  • mcp__rankroot__amplify_edit_post outbound
  • mcp__rankroot__amplify_schedule_posts untrusted-input, 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/io.github.zachhhhh/rankroot/verify?hash=4d82ce07bcf98178db29b42a2fffda323061b2714fb0bacdc4de13250584e154" | jq -e '.changed == false'

Pinned hash 4d82ce07bcf9, from Nov 21, 2026, 06:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.zachhhhh/rankroot/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.zachhhhh/rankroot
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.zachhhhh/rankroot.svg)](https://radar.anlyon.com/servers/io.github.zachhhhh/rankroot)

Source: MCP Registry. Synced Oct 21, 2026, 18:52 UTC.

RankRoot: AI visibility audit MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the RankRoot: AI visibility audit MCP server safe?

No scan can promise that. What its definitions show: 16 tools, 11 of which can change, send or delete something, and 3 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 RankRoot: AI visibility audit MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the RankRoot: AI visibility audit 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 RankRoot: AI visibility audit MCP server have?

16 tools: 11 write, 5 read. audit_ai_visibility, audit_seo, check_core_web_vitals, generate_ai_visibility_files, check_ai_crawler_access, submit_launch, amplify_preview, amplify_create_campaign and 8 more.

Does the RankRoot: AI visibility audit MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the RankRoot: AI visibility audit MCP server send data to outside services?

11 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): audit_ai_visibility, audit_seo, check_core_web_vitals, generate_ai_visibility_files, check_ai_crawler_access, validate_llms_txt and 5 more.

Has the RankRoot: AI visibility audit MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.