MCP App Store
by KeenEthics
Sitelemetry icon

Sitelemetry MCP Server for Claude and ChatGPT

By Egenil Teleferik

Overview

Sitelemetry gives Claude a structured, non-mutating assessment of a website covered by the authenticated customer's exact workspace verification. It checks security posture, technical SEO, AI-search visibility, analytics and tracking integrations, WCAG-oriented accessibility, Core Web Vitals, or all six pillars together. Results contain prioritized findings, evidence, impact, passing checks and remediation guidance, plus one authenticated report URL that remains stable during its report-retention window of up to 30 days. The Claude profile is verified-only and rejects an unverified target before an audit module runs. It blocks private-network destinations, revalidates every redirect hop, binds OAuth tokens to the exact Claude MCP resource, and enforces rate, quota and concurrency controls. The connector does not modify the target, initiate payments, expose plan/pricing links, or request Claude conversation history, memory or unrelated files.

How to connect

  1. Claude: Open the Sitelemetry listing in the Claude connectors directory and choose Connect. Claude listing Sitelemetry exposes 7 tools here.
  2. ChatGPT: Open the Sitelemetry listing in the ChatGPT app directory and choose Connect. ChatGPT listing Sitelemetry exposes 7 tools here.

Tools

audit_accessibility

ChatGPT
Static WCAG 2.2 accessibility audit from the DOM: image alt text, form labels, heading structure, landmarks, color-contrast signals, language attribute, duplicate ids, iframe titles. Returns violations with fixes.

audit_ai_visibility

ChatGPT
Assess how ready a site's content is to be found and cited by AI search and LLM assistants: entity clarity, answerability, prompt coverage, source signals, llms.txt/AI-crawler policy. Questions are checked against the site's own content; no AI provider is queried. If the connected account does not include AI visibility audits, it returns a not-started notice that uses no allowance. A completed audit uses the account's audit allowance. Repeating a call can run another audit and use more allowance. Returns findings with fixes.

audit_full

ChatGPT
Run every audit area the connected account includes (security, technical SEO, AI visibility, integrations, accessibility, performance) in one call and return a combined score across the measured areas, a summary per area in pillars, and prioritized cross-area findings with evidence and fixes. A security-only account gets the security area only. The security area follows the audit_security defaults without engine-* modules: active checks such as port and injection probes run only on a target whose host the account has verified, where the account includes them. On an unverified target, a security-only account gets public security checks and other accounts get a not-started notice that uses no allowance. Its checks send read-style requests and benign probes and can appear in the site's logs. The performance area sends the target URL to Google PageSpeed Insights. A completed audit uses the account's audit allowance. Repeating a call can run another audit and use more allowance. Use for a complete health check or an audit-fix-retest loop.

audit_integrations

ChatGPT
Detect and audit the analytics/tag/marketing-pixel/verification/consent stack from the site HTML + headers: GA4, GTM, Meta Pixel, TikTok/LinkedIn pixels, Search Console/Bing verification, Hotjar/Clarity, consent/CMP, and PII-in-dataLayer leaks. Returns gaps + fixes.

audit_performance

ChatGPT
Measure performance via Google PageSpeed Insights (Lighthouse lab + CrUX field data): LCP, INP, CLS, FCP, TTFB, and the top improvement opportunities. Returns findings with fixes. (Uses the operator PAGESPEED_API_KEY when set.)

audit_security

ChatGPT
Audit the security of a website you own or are authorized to assess. With profile and modules omitted, it runs the baseline checks included in the connected account, without external scanner engines. Public checks (DNS, email, domain, TLS, HTTP headers, HTTPS, technology and transport delivery signals) need no ownership verification, so a public-only module selection also runs on an unverified target. On a target whose host the account has verified, it can add active checks such as port and injection probes where the account includes them. On an unverified target the default runs public checks only or returns a not-started notice that uses no allowance. Built-in checks send read-style requests and benign probes that are not meant to change the site but can appear in its logs or alerts. A completed audit uses the account's audit allowance. Repeating a call can run another audit and use more allowance. Returns findings with severity, evidence and fixes.

audit_seo

ChatGPT
Crawl a site and audit technical SEO: crawlability, indexation, titles/meta, headings, canonical, structured data, broken internal links, redirect chains, AI-crawler policy. Available Search Console evidence from the account's existing Google connection is added unless includeSearchConsole is false. If the connected account does not include SEO audits, it returns a not-started notice that uses no allowance. A completed audit uses the account's audit allowance. Repeating a call can run another audit and use more allowance. Returns prioritized findings with fixes.

audit_accessibility

Claude

audit_ai_visibility

Claude

audit_full

Claude

audit_integrations

Claude

audit_performance

Claude

audit_security

Claude

audit_seo

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/sitelemetry"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/sitelemetry)