SEO Audit in ChatGPT

Questions it answers

Find what to fix on a public website, for search engines and for AI answers.

- audit_site: SEO audit of up to 25 pages, failed rules by priority with the fix and source, a row per page with broken internal links and images without alt, plus AI-search steps for the site owner. - audit_page: the same page rules for one address. - local_ai_readiness: whether a local business site is ready to be named in AI search. - score_page_citation: a 0 to 100 citation score for one page, with fixes by biggest gain. - compare_citations: what the pages an AI answer cited share that your page lacks. - find_ai_questions: long searches to answer, from a pasted Search Console export. - check_ai_instructions: checks a site's llms.txt, llms-full.txt and AI page. - generate_ai_instructions: drafts an llms.txt for the owner to review. - audit_ai_search: grades a site on 12 on-site checks AI answer engines rely on, pass, partial or fail, with the 3 biggest fixes, plus 15 AEO/GEO rows from Microsoft's guide to AEO and GEO.

It reads only the public sites you name, respects robots.txt and refuses private addresses. It does not run JavaScript, query search or AI engines, fetch directories, or measure rankings, traffic or backlinks. Scores and checks do not promise a citation or an effect on AI search answers.

Nothing about you or the site is stored. Answers are cached for ten minutes. The optional judgement step, off by default, sends page text to a language model service. It and local checks are limited per day.

What it can do

• Audits up to 25 pages of a site from its homepage and sitemap, with robots.txt respected
• Returns failed rules grouped by priority with the affected pages, the fix and the documentation link
• Checks titles, descriptions, headings, canonicals, noindex, structured data, share tags and image alt text
• Finds broken links, redirect chains, sitemap problems, thin and duplicate content
• Checks local business markup: name, address, phone, hours, map, and that the details match the page
• Compares pages: near-identical templated pages, little own text, hreflang returns, sitemap pages nothing links to
• Adds AI-search steps to a site audit: search engine webmaster reports, IndexNow, content, with sources
• Audits one page with the full page rule set
• Optional judgement of page purpose and competing pages, limited per day
• Checks local AI-search readiness: services, locations, prices, FAQ, schema, NAP, proof
• Checks llms.txt, llms-full.txt, an AI page, home links, and name, product and fact consistency
• Drafts an llms.txt from the site's own public pages for the owner to review
• Grades 12 AI-search checks from a site's own pages, each pass, partial, fail or unknown, with the top 3 fixes
• Checks 15 AEO/GEO rows from Microsoft's guide: markup fields, FAQ, dates, crawler parity and access, trust signals
• Scores one page from 0 to 100 for citation chance, with fixes by biggest gain
• Compares pages an AI answer cited with yours: opening answer, headings, table, list, date, links out, schema
• Ranks 7+ word searches in a pasted Search Console export, with page, question heading and answer skeleton

Tools

• audit_site, SEO audit (site). Use this to audit a whole site or several pages for SEO; it finds the pages itself. Never guess page addresses for requests such as "audit example.com", "which pages are worst?" or "my site has a page per city, are they too similar?". Pass the domain and optionally max_pages. Reads the homepage, sitemap and linked pages of that site, respecting robots.txt. Returns failed rules by priority, each with its pages, fix and docs link, plus a row per page with its status, broken internal links and images without alt text. It also compares pages: near-identical templated pages, pages with little own text, hreflang without return links or x-default, and sitemap pages nothing links to. Leave judge off unless the user asks what pages are for or which compete. It reads a sample, runs no JavaScript and measures no rankings, traffic or backlinks. For one named page use audit_page. Not for private or local addresses or to collect a site's content.
• score_page_citation, Citation score (page). Cite-chance score for one page, 0 to 100. Use this when the user asks whether ChatGPT, Perplexity or Google AI Overviews are likely to cite a page, or how to fix that. Pass exactly one of url, html, text, or sample. Returns the score and a fix list ordered by the biggest point gain. The checks cover an answer in the opening, question headings, an FAQ block, structured data, lists and tables, heading order, short sentences, a number with a source, a recent date, and an author line. Pasted html and text are scored as given and are not fetched. A url is one public page, with robots.txt respected. It does not call an AI engine and it does not promise a citation. Use compare_citations when the user has the pages an AI answer cited. Do not use it for private or local addresses, rankings, or traffic.
• find_ai_questions, Questions for AI search. Long-search finder for a pasted Search Console export. Use this when the user pastes Search Console Performance rows or a CSV and asks which questions to answer on their pages, or how to get named in ChatGPT or Google AI answers. Pass the text as csv, or JSON rows as rows, with query and impressions, and page if there is one. Up to 5000 rows. Returns the searches of 7 or more words ranked by impressions, marked when they look like questions. Each has the page Google shows, the question as a heading, and a 2-sentence answer skeleton with a placeholder for one real number or fact that only the owner knows. Also groups by page. It reads only what is pasted: no Google login, no Search Console call, no AI engine. It does not write the answer or invent the number. Not for a user with no export: ask them to paste one.
• compare_citations, Compare cited pages. Citation-pattern check for one query. Use this when the user has the pages an AI answer or Google AI Overview cited for a search and asks what they share, or why their own page is not cited. Pass query, cited_urls (2 to 6 public addresses the user copied from the answer) and exactly one of url, html or text for the user's page. Reads the public pages with robots.txt respected and returns the gaps first: each signal most cited pages share and the user's page lacks (opening answer, query words in a heading, question heading, table, list, date in the last year, links out, schema types, length), with counts such as 4 of 5 and a fix. Every signal is also listed per page. It reads no Google or AI engine, so the user must supply the cited addresses; never guess them. It stores nothing; change over days needs a new call later. A shared signal is a pattern in a small sample, not a proven cause, and no citation is promised. Do not use it for private addresses.
• audit_page, SEO audit (page). Use this only for a single page address the user gave, such as "what SEO problems does https://example.com/docs have?" or "is the title and description of this page OK?". Pass the page address. Returns the page rules that failed grouped by priority, each with the fix and the documentation link, plus the title, description, headings and other facts read. robots.txt is respected. For several pages, a whole site or finding pages, call audit_site once instead: it also runs the rules that compare pages or read the sitemap. Not for private or local addresses, rankings, traffic or reading a page's text. It does not measure speed or Core Web Vitals (LCP, CLS, INP); reach_check gives server response time per region.
• local_ai_readiness, Local AI-search readiness. Local-business readiness for AI search answers. Use this when the user asks if a local business site is ready to be named by AI search, ChatGPT, Gemini or similar, or what to fix so assistants can cite it. Pass the business's own site. Crawls only that site's public pages (robots.txt respected, up to 25, default 15) and returns pass, warn or fail for a page per service, location or service-area pages, visible prices, FAQ, LocalBusiness schema (name, address, phone, hours, geo, sameAs), NAP consistency, on-site proof, a one-line description and recent dated content. Each check has the evidence URL and a fix. Also returns what Gemini, OpenAI and Anthropic leaned on in a Yext study and profile advice, which is not fetched. It does not query AI engines, directories or review sites, or measure rankings. Not for a site with no physical location or service area: use audit_site. Do not use it for private addresses or to collect contact details.
• check_ai_instructions, Check AI instructions. Checks the site's AI instructions files and page. Use this when the user asks whether a site publishes llms.txt, llms-full.txt or an AI instructions page, whether the home page links to them, and whether the file matches the site's own name, products and facts. Pass the domain. Returns pass, warn or fail for each part, with the evidence URL and a fix, plus the date the pages were read. A public post is cited as the reason the check exists. It does not promise an effect on AI Overviews and does not query AI engines. For a local business site, use local_ai_readiness; to draft the file, use generate_ai_instructions. Do not use it for private addresses or to collect contact details.
• generate_ai_instructions, Draft an llms.txt. Drafts an llms.txt from the site's own public pages. Use this when the owner wants a draft AI instructions file to review. Pass the domain. Returns markdown for the owner to edit and publish themselves. Nothing is written to the site. A public post is cited as the reason the draft exists. It does not promise an effect on AI Overviews and does not query AI engines. Do not use it for private addresses or to collect contact details.
• audit_ai_search, AI search audit (12 checks). Grades a site on 12 on-site checks for AI search. Use it when the user asks whether ChatGPT, Claude, Perplexity or Google AI would recommend or cite their site, or wants a GEO audit. Pass the domain. Reads up to 10 public pages without JavaScript (robots.txt respected). Each check is pass, partial, fail or unknown with evidence and a fix: no-JS text, crawler access, llms.txt, what-is sentence, prices page, comparison page, 10 questions, Organization and Product markup, one name, named quotes, dates, an original number. Returns a score out of 12 and the 3 biggest fixes. unknown means the fetch could not prove the row and earns no point. Also 15 AEO/GEO rows from Microsoft's guide, pass, warn or fail. It does not query AI engines or promise a citation. Not for private addresses.

Add SEO Audit in ChatGPT

ChatGPT does not read a local config file. A custom MCP server is added in the product, and only after developer mode is on. These steps were checked against OpenAI's plugin connect guide and the ChatGPT MCP guide on 2026-10-01. Developer mode can be hidden by a workspace policy, so a Team or Enterprise admin may have to allow it first.

1. Open ChatGPT settings, then Security and login, and turn on Developer mode.
2. Open ChatGPT plugins and select the plus button.
3. Enter a name such as "SEO Audit" and a one-line description of what you want it to answer.
4. Under Connection, choose the public endpoint and paste this URL. Include the /mcp path. Do not add a tunnel id: this server is already public.

   https://seoaudit.openkrill.app/mcp

5. Create the connection and review the tools ChatGPT lists. You should see audit_site, score_page_citation, find_ai_questions, compare_citations, audit_page, local_ai_readiness, check_ai_instructions, generate_ai_instructions, audit_ai_search. The feedback tools on the same server are optional and not required for the lookup.
6. Start a new conversation, add the connection from the tools menu, and ask: Audit example.com for SEO problems

No API key and no OAuth client id are required. The server answers without a login. Calls are limited per network and per day, and a limit comes back as a tool error rather than a partial answer. If the tool list is stale after a server change, open the connection and select Refresh, then start a new conversation.

The ChatGPT desktop app, Codex CLI and IDE extension share a different config. In the desktop app, open Settings, then MCP servers, choose Add server, select Streamable HTTP, and paste the same URL. In ~/.codex/config.toml the equivalent is a table named mcp_servers.seo-audit with url = "https://seoaudit.openkrill.app/mcp". ChatGPT on the web does not read that file. A published directory listing is also a different path: this page is the developer-mode connection, not a claim that SEO Audit is already in the ChatGPT directory.

Treat the server as untrusted until you have read a few answers. A remote MCP server sees the arguments the model sends. SEO Audit is read-only and documents what it sends onward on the privacy page.

If it does not work

A call checked on 2026-10-17

example.com is one public page. Judgement stays off, so no page text is sent to a language model. The request below was posted to https://seoaudit.openkrill.app/mcp as tools/call. HTTP 200. Source: the SEO Audit server, read 2026-10-17.

{
  "method": "tools/call",
  "params": {
    "name": "audit_page",
    "arguments": {
      "url": "https://example.com",
      "judge": false
    }
  }
}

• status. 200
• notice. This is what the site served to a request from Agent Tools servers right now, read with robots.txt respected and without running JavaScript. The rules follow Google Search Central documentation and common conventions; ru
• url. https://example.com/
• finalUrl. https://example.com/

Repeat the call yourself if you need a newer reading. Cached answers expire. A rate limit is not a result: wait and try again. Nothing in the call is a ranking, a filing, or advice.

Using it in production

Nothing to install and nothing to run: no package, no Python or Node.js version and no environment variable. SEO Audit runs on our servers, and your client only needs the URL https://seoaudit.openkrill.app/mcp.

Use it in other apps

• SEO Audit in Claude
• SEO Audit in Cursor
• SEO Audit in VS Code
• SEO Audit in Pi

Roles that use SEO Audit

• SEO specialist guide

Frequently asked questions

Words on this page

• MCP (Model Context Protocol) definition
• Streamable HTTP transport definition
• Tool primitive definition
• Rate limit policy definition

Source: plugin listing for seo-audit in this repository, and a live tools/call on 2026-10-17. As of 2026-10-17.