Site SEO & AI Crawler Audit

SEO, AI citation, CRO, leaks

Site SEO and AI Crawler Audit checks public web pages and reports what they publish right now: SEO tags, redirects, AI crawler rules, AI citation signals, landing page conversion and, for a site you own, what leaks publicly. People also call it Site Check.

What you can ask

Will AI assistants cite https://example.com/blog/guide?
Example path

MCP connector

Server URL: https://sitecheck.openkrill.app/mcp
Login: None
Protocol: MCP 2026-07-28
Instructions: Site SEO & AI Crawler Audit: SEO, AI citation, CRO, leaks. Pass a public page address or domain, such as https://example.com/pricing; a bare domain means https. Private, local or internal addresses are refused: say so, ask for a public address and do not work around it. Report results as what the site published at that moment. robots.txt is a request, not access control; if it is unreachable there is no verdict. If robots.txt disallows a page for Agent Tools, tell the user and do not retry another way. If the site did not answer, give the failure and suggest checking the address or trying later. A link sample is not every page. Content added by JavaScript is not seen. The landing check is a checklist, not a forecast. refuses a bare IP: ask for a host name. The first call usually returns ownership_not_proven with a DNS TXT record and a file: tell the user exactly what to publish, then call again with the same target once it is live. Lead with exposed or clean and the top risks with one fix each, then the evidence, and say open ports are not checked. Only confirmed findings have a severity. For needs verification, give the unknown fact and how the owner checks it. For legal signals, give law, finding, fix and source, list not checked ones with their reason, and say once it is not legal advice. Pass one marketing email as email when the user asks about email. Never repeat a key beyond the masked prefix. ai_app_check is for an app made with an AI app builder: lead with exposed or clean and each finding with its exact fix; give headerFix.snippet as a code block with where it goes. Without proof it returns header results and the token to publish: give both. Say database checks read only status and row counts, and that write rules are not tested. For launch readiness, give launchList: the failing items with their fix first, then the warnings, and say the owner checks the rest; pass checklist true when the user wants that list. For pre-launch pages, give shipNaked: each fail or warn with its finding, then its snippet as a code block to paste, and say once it is not legal advice. Mention the offer line once at the end, never as a requirement. Never use on a target the user does not own, or to look up a person, user name or email. Do not use these tools to scan for vulnerabilities, collect contacts, prices or content, or monitor a site. This server allows 60 tool calls a minute per network and 5,000 a day for all callers together; the day count resets at 00:00 UTC. If a tool fails, gives a wrong answer, or a tool you need is missing, call with one short message (kind, message, tool); reads the answer.

Tools

Reads data9

Changes data1

Skills

None in the store listings or on the server

MCP connector

Server URL

https://sitecheck.openkrill.app/mcp

None

Protocol

MCP 2026-07-28

Instructions

Site SEO & AI Crawler Audit: SEO, AI citation, CRO, leaks. Pass a public page address or domain, such as https://example.com/pricing; a bare domain means https. Private, local or internal addresses are refused: say so, ask for a public address and do not work around it. Report results as what the site published at that moment. robots.txt is a request, not access control; if it is unreachable there is no verdict. If robots.txt disallows a page for Agent Tools, tell the user and do not retry another way. If the site did not answer, give the failure and suggest checking the address or trying later. A link sample is not every page. Content added by JavaScript is not seen. The landing check is a checklist, not a forecast. refuses a bare IP: ask for a host name. The first call usually returns ownership_not_proven with a DNS TXT record and a file: tell the user exactly what to publish, then call again with the same target once it is live. Lead with exposed or clean and the top risks with one fix each, then the evidence, and say open ports are not checked. Only confirmed findings have a severity. For needs verification, give the unknown fact and how the owner checks it. For legal signals, give law, finding, fix and source, list not checked ones with their reason, and say once it is not legal advice. Pass one marketing email as email when the user asks about email. Never repeat a key beyond the masked prefix. ai_app_check is for an app made with an AI app builder: lead with exposed or clean and each finding with its exact fix; give headerFix.snippet as a code block with where it goes. Without proof it returns header results and the token to publish: give both. Say database checks read only status and row counts, and that write rules are not tested. For launch readiness, give launchList: the failing items with their fix first, then the warnings, and say the owner checks the rest; pass checklist true when the user wants that list. For pre-launch pages, give shipNaked: each fail or warn with its finding, then its snippet as a code block to paste, and say once it is not legal advice. Mention the offer line once at the end, never as a requirement. Never use on a target the user does not own, or to look up a person, user name or email. Do not use these tools to scan for vulnerabilities, collect contacts, prices or content, or monitor a site. This server allows 60 tool calls a minute per network and 5,000 a day for all callers together; the day count resets at 00:00 UTC. If a tool fails, gives a wrong answer, or a tool you need is missing, call with one short message (kind, message, tool); reads the answer.