ayrank-tools
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ayrank-tools Check whether GPTBot can crawl example.com and validate its sitemap."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ayrank-mcp
An MCP server for the free AY Rank tools API. It gives an AI agent the same checks as https://www.ayrank.com/tools: AI crawler access, robots.txt tests, sitemap and hreflang validation, response headers, page size, headings, alt text, internal and broken links, trust signals, IndexNow and AI Overview eligibility. No API key.
The API allows 30 requests per 60 seconds per IP across all tools. The server keeps to that limit on its side too.
Tools
18 read tools, each one a GET on one endpoint of the API:
Tool | What it does | Endpoint |
| Can GPTBot, ClaudeBot, PerplexityBot and Google-Extended crawl the homepage | /api/v1/ai-crawler-access-checker |
| Test one URL against robots.txt for one user agent | /api/v1/robots-txt-tester |
| Bing AI training and grounding, Google-Extended | /api/v1/ai-training-grounding-checker |
| Published IP ranges of AI and search crawlers | /api/v1/ai-crawler-ip-ranges |
| Google's stated conditions for AI Overviews and AI Mode links | /api/v1/ai-overview-eligibility-checker |
| Validate an XML sitemap and spot-check its URLs | /api/v1/sitemap-validator |
| Check one page's hreflang set and its alternates | /api/v1/hreflang-checker |
| Every response header, hop by hop | /api/v1/http-header-checker |
| Size against Googlebot's 2 MB limit | /api/v1/page-size-checker |
| h1 to h6 outline and its issues | /api/v1/heading-outline-checker |
| Images and their alt text | /api/v1/alt-text-checker |
| Internal links on one page with anchors | /api/v1/internal-link-checker |
| Status of up to 100 links on one page | /api/v1/broken-link-checker |
| 11 trust signals of an article | /api/v1/eeat-checker |
| Is the IndexNow key file live and matching | /api/v1/indexnow-checker |
| Score a title from 0 to 100 | /api/v1/title-scorer |
| Draft an llms.txt (returns text, writes nothing) | /api/v1/llms-txt-generator |
| Draft a robots.txt (returns text, writes nothing) | /api/v1/robots-txt-generator |
One info tool:
ayrank_tracking_infomakes no network call. See "Tracking" below.
Two write tools, off by default:
ayrank_request_free_auditasks for the free AY Rank AI visibility audit. It posts to https://www.ayrank.com/api/lead with sourcemcpand creates a lead and notifies the AY Rank team; nothing is emailed to you or anyone else. A person from the team follows up within 24 hours. The tool does not run the audit itself.ayrank_indexnow_submitsends up to 100 URLs on a host you control to IndexNow. The AY Rank API re-checks your key file first, then posts the URLs to api.indexnow.org.
Related MCP server: seo-audit-mcp
Tracking
This server does not track whether ChatGPT, Perplexity, Gemini, Claude or Google AI answers name or cite your brand. The free API never asks an AI assistant anything.
The free check at app.ayrank.com runs in a browser only: 3 buyer questions, one assistant answering from what it knows, no live web search, no API.
Daily tracking with live search is in the paid AY Rank app (7-day free trial). The app has its own MCP server that needs a key from your workspace. Its set-up guide is at https://app.ayrank.com/docs/skills.
ayrank_tracking_info returns the same facts and links to the agent.
Write gate
A write tool sends a request only when both are true:
the call passes
confirm: true, andthe server runs with
AYRANK_MCP_ALLOW_WRITES=1in its environment.
Otherwise it sends nothing and returns a dry run: the method, the URL, the exact JSON body and what would happen. Each write tool runs at most once per 60 seconds and 5 times per server process. Every endpoint is free, so no tool spends money.
Install
The package is not on npm. Install it from this GitHub repo and build it locally. You need Node.js 20 or newer and git.
git clone --branch v0.1.0 --depth 1 https://github.com/ay-automate/ayrank-mcp.git
cd ayrank-mcp
npm ci
npm run build
pwdnpm ci installs the exact versions in package-lock.json. The last line prints the folder; below it is written as /path/to/ayrank-mcp.
Claude Code
claude mcp add ayrank-tools -- node /path/to/ayrank-mcp/dist/src/index.jsWith the write tools turned on:
claude mcp add ayrank-tools -e AYRANK_MCP_ALLOW_WRITES=1 -- node /path/to/ayrank-mcp/dist/src/index.jsThe name is ayrank-tools, so it does not clash with the AY Rank app's own MCP server, which its guide adds as ayrank.
Claude Desktop
Add this to claude_desktop_config.json (Settings, Developer, Edit Config), then restart Claude Desktop:
{
"mcpServers": {
"ayrank-tools": {
"command": "node",
"args": ["/path/to/ayrank-mcp/dist/src/index.js"]
}
}
}To turn on the write tools, add "env": { "AYRANK_MCP_ALLOW_WRITES": "1" } next to args.
Cursor
Add this to .cursor/mcp.json in a project, or to ~/.cursor/mcp.json for every project:
{
"mcpServers": {
"ayrank-tools": {
"command": "node",
"args": ["/path/to/ayrank-mcp/dist/src/index.js"]
}
}
}Streamable HTTP
node /path/to/ayrank-mcp/dist/src/index.js --http --port 3333It listens on http://127.0.0.1:3333/mcp only, stateless, POST only.
Settings
Variable | Default | Meaning |
| unset |
|
| API base URL, used by the tests to point at a local stub |
Development
npm ci
npm run build
npm test # every tool against a local stub, plus stdio and HTTP transports
npm run test:live # one live read per read tool on www.ayrank.com, writes as dry runs only
npm run validate:server-json # server.json against the MCP registry schemaMIT licensed.
Available Tools
21 toolsayrank_ai_crawler_accessAI crawler accessARead-only
Use to check whether GPTBot, ClaudeBot, PerplexityBot and Google-Extended may crawl a site's homepage under its robots.txt, plus the homepage's meta robots and X-Robots-Tag rules for them. Returns allowed or blocked per bot with the deciding line. Not for one specific page or another user agent (use ayrank_robots_txt_test), and it cannot see CDN or firewall rules that fire only for the real bots, because it sends an AY Rank user agent. Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: domain (required).
ayrank_ai_crawler_ip_rangesAI crawler IP rangesARead-only
Use to get the CIDR ranges that OpenAI, Perplexity, Anthropic, Google, Bing, Apple, Common Crawl and Mistral publish for their crawlers and agents, for example to tell a real GPTBot hit in server logs from a fake one. Each source says whether it is live or a dated snapshot. Cached for 24 hours. No input. Not for checking whether a bot may crawl a site (use ayrank_ai_crawler_access).
Inputs: no named parameters.
ayrank_ai_overview_eligibilityAI Overview eligibilityARead-only
Use to check one URL against Google's stated conditions for being a supporting link in AI Overviews and AI Mode: robots.txt, status, noindex, unavailable_after, nosnippet and max-snippet, data-nosnippet share and canonical. Returns eligible, not-eligible or cant-check with evidence per check. Eligible never means included, and it cannot tell whether the page is indexed (only Search Console can). It does not check whether Google shows the page in an AI answer. Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: url (required).
ayrank_ai_training_groundingAI training and grounding preferencesARead-only
Use to read a page's AI training and grounding preferences: Bing AI Training (robots.txt __usage_ai-training group, page meta or X-Robots-Tag), Bing AI Grounding (page level), Google-Extended, and whether Bingbot and Googlebot may crawl the path. Only directives from Bing's and Google's 30 Oct 2026 posts. Not for the other AI crawlers (use ayrank_ai_crawler_access).
Inputs: url (required).
ayrank_alt_textAlt text checkerARead-only
Use to list a page's images (img, input type=image, area, svg role=img) with their alt text state: missing, empty, present or hidden, and flags such as missing alt, unnamed image links or file-name alt. It does not judge alt text quality and does not download images. Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: url (required).
ayrank_broken_linksBroken link checkerARead-only
Use to find broken links on one page: AY Rank's server sends one GET to each of up to 100 links on it and reports ok, redirect, broken, denied, rate-limited, server-error, timeout and so on. Takes up to 25 s. Not a site crawl. Not for anchor text review (use ayrank_internal_links). Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: url (required).
ayrank_eeat_signalsE-E-A-T trust signalsARead-only
Use to list 11 trust signals an article shows (byline, author page link, Article and Person JSON-LD, published and updated dates, About and Contact links, outbound links), each found or missing with evidence. Google says E-E-A-T is not a ranking factor by itself, so there is a found count and no score. Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: url (required).
ayrank_heading_outlineHeading outlineARead-only
Use to list a page's h1 to h6 headings in order with level, announced text and landmark, and flag no h1, skipped levels, empty or image-only headings. More than one h1 is a note only. Not a content quality score. Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: url (required).
ayrank_hreflang_checkhreflang checkerARead-only
Use to check one page's hreflang set (link tags in the head and the HTTP Link header) against Google's rules: valid codes, self-reference, x-default, absolute URLs, then whether up to 10 alternates answer, link back and self-canonicalize. Sitemap hreflang is not read. Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: url (required).
ayrank_http_headersHTTP header checkerARead-only
Use to list every response header of a URL hop by hop (redirects followed by hand, at most 5) and parse X-Robots-Tag, Link, Content-Type, Cache-Control, ETag, Last-Modified, Vary and Content-Encoding into issues such as noindex headers, redirect chains or temporary redirects. The body is never read. Headers are as seen from AY Rank's server; a CDN can answer differently by region or user agent.
Inputs: url (required).
ayrank_indexnow_key_checkIndexNow key checkARead-only
Use to check that an IndexNow key file is live and matches the key (step 1 of IndexNow). Nothing is sent to IndexNow. To submit URLs after it passes, use ayrank_indexnow_submit.
Inputs: key (required), host (required), keyLocation.
ayrank_indexnow_submitSubmit URLs to IndexNowA
Use to submit up to 100 URLs on a host you control to IndexNow (step 2, after ayrank_indexnow_key_check passes). The AY Rank API checks the URLs and re-checks the key file, then posts them to api.indexnow.org, which shares them with the search engines that take part in IndexNow. Gated: without confirm: true and AYRANK_MCP_ALLOW_WRITES=1 on the server it returns a dry run and sends nothing. At most once per 60 seconds. Not for sites you do not control.
Inputs: key (required), host (required), urlList (required), confirm, +1 more.
ayrank_internal_linksInternal link checkerARead-only
Use to list the internal links on ONE page with anchor text, rel and position (main, nav, footer), grouped by target, with flags for empty or generic anchors, nofollow, self-links and links Google cannot crawl. It does not crawl the site and does not fetch the links (use ayrank_broken_links for status codes). Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: url (required).
ayrank_llms_txt_generatellms.txt generatorARead-only
Use to draft an llms.txt file from company details, with a completeness score. It returns text only and writes nothing to any site. It does not read the site, so it only knows what you pass in.
Inputs: websiteUrl (required), companyName (required), industry, keyPages, +5 more.
ayrank_page_sizePage size checkerARead-only
Use to measure a URL's transferred and decoded size against Googlebot's 2 MB limit (64 MB for PDF), and for HTML see what sits past the cut and which parts (inline scripts, JSON, Next.js payload, styles, svg) take the bytes. Linked CSS, scripts and images are not fetched. No ranking claim. Free AY Rank API, no key. JavaScript is not run, so content added by scripts is not seen.
Inputs: url (required).
ayrank_request_free_auditRequest a free AI visibility auditA
Use only when the user asks for the free AY Rank AI visibility audit and gives their own email and website. It creates a lead and notifies the AY Rank team; nothing is emailed to you or anyone else. A person from the AY Rank team follows up within 24 hours; this tool does not run the audit itself. Gated: without confirm: true and AYRANK_MCP_ALLOW_WRITES=1 on the server it returns a dry run and sends nothing. At most once per 60 seconds. Never call it with an email the user did not give you.
Inputs: email (required), website (required), name, notes, +2 more.
ayrank_robots_txt_generaterobots.txt generatorARead-only
Use to draft a robots.txt that allows every known crawler except the ones listed in block. It returns text only and writes nothing to any site. Not for testing an existing robots.txt (use ayrank_robots_txt_test).
Inputs: block, sitemapUrl, blockedDirs.
ayrank_robots_txt_testrobots.txt testerARead-only
Use to test one URL against the site's robots.txt for one user agent (RFC 9309: named group else *, longest match, Allow wins a tie). Returns allowed, the deciding line and lines that decide nothing. Not for meta robots or X-Robots-Tag (use ayrank_http_headers or ayrank_ai_overview_eligibility), and it does not write a robots.txt (use ayrank_robots_txt_generate).
Inputs: url (required), userAgent.
ayrank_sitemap_validateSitemap validatorARead-only
Use to validate an XML sitemap (or find it from a site root via robots.txt, else /sitemap.xml) against the sitemaps.org protocol and Google's rules, including up to 10 child sitemaps of an index, then spot-check up to 20 listed URLs with HEAD. Not for checking every URL in a large sitemap, and not for hreflang in sitemaps.
Inputs: url (required).
ayrank_title_scoreTitle scorerARead-only
Use to score a page title from 0 to 100 on eight factors (length, power words, numbers, emotion, question format, readability, AI citability, uniqueness) with a tip per factor. It is a heuristic, not a measure of rankings or clicks. Reads no page.
Inputs: title (required).
ayrank_tracking_infoAI answer tracking: what existsARead-only
Use when someone asks to track whether ChatGPT, Perplexity, Gemini, Claude or Google AI answers name or cite a brand. This server cannot do that: the free AY Rank API never asks any AI assistant anything. This tool returns where tracking does exist (the paid AY Rank app and its own MCP server) and the free one-off check. Makes no network call.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 21 tools
Every tool targets a single, narrow artifact (robots.txt, sitemap, hreflang set, headers, headings, alt text, links, title, llms.txt, IndexNow, AI crawler access), and most descriptions explicitly name the neighbouring tool to use instead. The closest pairs (robots_txt_test vs ai_crawler_access, internal_links vs broken_links) are clearly delimited by input scope and output. An agent should almost never misselect here.
All names share a strict ayrank_ prefix and snake_case, which is highly predictable. However the ordering convention is mixed: some are noun-first (ayrank_http_headers, ayrank_alt_text, ayrank_internal_links) and others verb-first (ayrank_sitemap_validate, ayrank_hreflang_check, ayrank_title_score). Readable and grouped, but not a single uniform pattern.
21 tools is at the upper end of comfortable, but each one covers a distinct audit check with no redundancy, so nothing feels padded. A slightly heavier surface than ideal for a single-purpose SEO/AI-visibility server, though justified by the breadth of checks.
The surface covers a full inspection lifecycle: crawler access, robots.txt/sitemap/hreflang validation and generation, on-page structure, links, headers, size, E-E-A-T, llms.txt, IndexNow submission, and AI Overview eligibility, plus honest boundary tools (tracking_info, request_free_audit). Gaps remain around canonical handling as a standalone check, structured-data validation beyond Article/Person, and performance/vitals, but these are workaroundable or explicitly out of the free API's scope.
Maintenance
Related MCP Connectors
Free SEO, GEO, and AEO audits: analyze any page or domain, AI-crawler access, agent readiness.
Free technical SEO, AEO, LLMO and GEO checks for AI agents: check a page, fix it, verify the fix.
Free SEO/GEO audits of public websites and AI answer-engine citation checks. No login or API key.
Live AEO, GEO, JSON-LD Schema, robots.txt AI crawler, and Agent Readiness diagnostic auditor.
Related MCP Servers
AlicenseBqualityCmaintenanceSEO + GEO MCP server: live Google Search Console & GA4 data, keyword and page analysis, AI-visibility tracking across ChatGPT, Claude, Gemini & Perplexity, site audit and SEO task management — all from chat.382MIT- AlicenseNot gradedqualityDmaintenanceEnables AI agents to perform instant SEO audits, check robots.txt, sitemaps, and AI crawler access for any URL without API keys.MIT
- AlicenseAqualityBmaintenanceAn MCP server that lets an AI agent audit a page for SEO and GEO — on-page tags, structured data, robots.txt, sitemaps, hreflang, and whether ChatGPT, Claude, Perplexity and Gemini can actually crawl and cite you. No API keys required.17395 npm1MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to run evidence-first technical SEO and GEO audits, inspect HTML, structured data, robots policies and sitemaps, and compare before/after reports to verify fixes.51MIT