Audit Core Web Vitals across your site with AI

The scenario

Google's page experience signals affect ranking, and Core Web Vitals are how that's measured. Manually running PageSpeed Insights on every important URL is slow; sharing one run is brittle (PSI scores swing 20+ points across runs). You want a single chat where the AI runs PSI on your top pages, surfaces both lab and field data, and prioritises fixes by potential ms savings.

The prompt

Use the gsc-pap MCP. For https://example.com, get my top 10 organic-traffic pages from the last 28 days via Search Console. For each one run pagespeed_insights mobile + pagespeed_field_data mobile. Build a table: page_path, perf_score, LCP_lab, LCP_field_p75, INP_field_p75, CLS_field_p75, and the #1 PSI opportunity by ms savings. Sort by perf_score asc so my worst-performing high-traffic pages bubble to the top.

What happens

1. 1

   AI fetches the top 10 organic-traffic pages

   Claude/Cursor calls `search_analytics_query` with dimension `page` for the last 28 days, takes the top 10 by clicks. This is your prioritisation set, fixing CWV on a page nobody visits is wasted effort.

2. 2

   AI loops PSI calls (parallel-safe)

   For each page the AI calls `pagespeed_insights(url, mobile)` and `pagespeed_field_data(url, mobile)`. Both share GSC PAP's PSI cache so this is at most one Google PSI hit per (url, mobile) pair per 24h.

3. 3

   AI builds the report and surfaces fixes

   Output is a sortable table with both lab and field metrics + the highest-impact opportunity per page. The AI also highlights pages where lab and field disagree (lab says fast, field says slow → environment-specific issue) or where field data is missing (low-traffic URL with no CrUX samples → fall back to lab and origin-level field data).

Outcome

Most sites uncover 2-3 'silent killers': pages with high organic traffic, decent lab scores, but field-level LCP > 3s for real users (typically because of an above-the-fold third-party script CrUX captures but the lab miss). Fixing these in priority order moves the page-experience signal from 'needs improvement' to 'good' for a meaningful chunk of your traffic.

Where to take it next

• ·Re-run weekly to catch regressions from new deploys.
• ·Pair with `correlate_gsc_to_ga4` to weight CWV fixes by actual revenue impact.
• ·For URL templates (e.g, blog posts or product pages) sample 3-5 representative URLs rather than auditing every one.