Sitelemetry

Authorized website audits for security, technical SEO, AI visibility, integrations, accessibility, and performance.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Audit.Security: Audit the website with every security module included in the connected account by default. Explicit profile, module and port selections are supported within that entitlement. Protected
  • Audit.Seo: Crawl a site and audit technical SEO: crawlability, indexation, titles/meta, headings, canonical, structured data, broken internal links, redirect chains, AI-crawler policy. Returns priorit
  • Audit.Ai Visibility: Assess how visible and citable a site is to AI search and LLMs (ChatGPT/Claude/Perplexity/Google AI): entity clarity, answerability, prompt coverage, source signals, llms.txt/AI-c

What data it sees

Do you need an account

No: the server works without sign-in

Authorized website audits for security, technical SEO, AI visibility, integrations, accessibility, and performance.

How to connect

How to connect Sitelemetry to Claude

The server address to paste into Claude settings:

https://sitelemetry--ozandikici.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Sitelemetry to ChatGPT

The server address to paste into ChatGPT settings:

https://sitelemetry--ozandikici.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Sitelemetry to Cursor

The server address to paste into Cursor settings:

https://sitelemetry--ozandikici.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (7)

Raw names from tools/list. Only developers need these.

audit.securityAudit the website with every security module included in the connected account by default. Explicit profile, module and port selections are supported within that entitlement. Protected checks require verified target ownership. Returns all observed findings and identifies unavailable measurements or engines. Long audits may return status: running with a jobId. Wait retryAfterMs, then call the same tool using the returned pollArguments (jobId only) until it returns the final result. If repeating other arguments, keep every original argument unchanged. Polling retrieves the same audit without starting another scan or reserving more quota. Do not present running as completed and do not start a replacement audit while it is running.
audit.seoCrawl a site and audit technical SEO: crawlability, indexation, titles/meta, headings, canonical, structured data, broken internal links, redirect chains, AI-crawler policy. Returns prioritized findings with fixes. Long audits may return status: running with a jobId. Wait retryAfterMs, then call the same tool using the returned pollArguments (jobId only) until it returns the final result. If repeating other arguments, keep every original argument unchanged. Polling retrieves the same audit without starting another scan or reserving more quota. Do not present running as completed and do not start a replacement audit while it is running.
audit.ai_visibilityAssess how visible and citable a site is to AI search and LLMs (ChatGPT/Claude/Perplexity/Google AI): entity clarity, answerability, prompt coverage, source signals, llms.txt/AI-crawler policy. Returns findings with fixes. Long audits may return status: running with a jobId. Wait retryAfterMs, then call the same tool using the returned pollArguments (jobId only) until it returns the final result. If repeating other arguments, keep every original argument unchanged. Polling retrieves the same audit without starting another scan or reserving more quota. Do not present running as completed and do not start a replacement audit while it is running.
audit.integrationsDetect 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. Long audits may return status: running with a jobId. Wait retryAfterMs, then call the same tool using the returned pollArguments (jobId only) until it returns the final result. If repeating other arguments, keep every original argument unchanged. Polling retrieves the same audit without starting another scan or reserving more quota. Do not present running as completed and do not start a replacement audit while it is running.
audit.accessibilityStatic 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. Long audits may return status: running with a jobId. Wait retryAfterMs, then call the same tool using the returned pollArguments (jobId only) until it returns the final result. If repeating other arguments, keep every original argument unchanged. Polling retrieves the same audit without starting another scan or reserving more quota. Do not present running as completed and do not start a replacement audit while it is running.
audit.performanceMeasure 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.) Long audits may return status: running with a jobId. Wait retryAfterMs, then call the same tool using the returned pollArguments (jobId only) until it returns the final result. If repeating other arguments, keep every original argument unchanged. Polling retrieves the same audit without starting another scan or reserving more quota. Do not present running as completed and do not start a replacement audit while it is running.
audit.fullRun all six audit pillars with the connected account’s complete security module scope and page/prompt allowances. Optional selections can narrow the scope. Returns detailed evidence and fixes without omitting findings; measurement limits and unavailable engines are explicit. Long audits may return status: running with a jobId. Wait retryAfterMs, then call the same tool using the returned pollArguments (jobId only) until it returns the final result. If repeating other arguments, keep every original argument unchanged. Polling retrieves the same audit without starting another scan or reserving more quota. Do not present running as completed and do not start a replacement audit while it is running.