Who it is forA marketing lead working on GEO who needs to know whether AI answer engines send visitors to the site.
The problemAI visibility is hard to judge from prompt-sampling estimates, and few teams check referral traffic from AI engines directly.
The outcomeA report of AI engines that refer traffic to the site, plus the pages those engines cite, based on GA4 AI-referral data.
What you need first
- Claude Code, or Claude with custom connectors (Cursor and other MCP clients can add the same URL)
- A Google account with access to the Search Console, GA4 and Google Ads properties you want to analyze
- A Ryze workspace sign-in, with Google Search Console and GA4 connected once
- The target domain, for example mysite.com
Steps
- Run
claude mcp add ryze --transport http https://connector.get-ryze.ai/mcpto connect the Ryze MCP. - Run
claude plugin marketplace add Ryze-AI-Adgent/open-seo-mcp-skills. - Run
claude plugin install open-seo-mcp-skills@ryze. - Ask Claude: "which AI engines send me traffic and which pages do they cite?"
- Review the pages that AI engines cite and decide which ones need stronger content.
Prompt for your agent
Using the open-seo-mcp-skills ai-visibility skill through the Ryze MCP, report which AI engines (ChatGPT, Perplexity, Claude, Gemini) send traffic to <target-domain> and which pages they cite. Return a table of engines, sessions and cited pages from GA4. Verify that the figures come from GA4 AI-referral reports and not from prompt-sampling estimates.
Caveat. The README says the Ryze workspace also tracks brand mentions in AI answers, but this skill's report is based on GA4 AI-referral traffic, so it shows referrals and cited pages only.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page