SEO · 1 skill

PageSpeed Insights MCP and Claude skills

Run PageSpeed Insights on your key pages, pull Core Web Vitals from real Chrome users along with the Lighthouse score, and report which pages got slower.

Connect PageSpeed Insights to your agent (MCP)

MCP server. Google doesn't publish an MCP server for PageSpeed Insights; community servers wrap the same API. The Chrome DevTools project does publish Chrome DevTools MCP, which records performance traces in a local Chrome and can add CrUX field data: claude mcp add --transport stdio chrome-devtools -- npx -y chrome-devtools-mcp@latest (source). Codex and Cursor run the same command.
PageSpeed Insights API with a key. The API answers occasional requests without a key; for scheduled runs, enable the PageSpeed Insights API in a Google Cloud project, create an API key restricted to it, and store it in PAGESPEED_API_KEY. Enable the Chrome UX Report API on the same key if the skill also reads CrUX history.
Lighthouse CLI. npx lighthouse https://example.com --only-categories=performance --output=json --quiet --chrome-flags="--headless" runs the lab test on your own machine or in CI.

All of this reads public performance data. Restrict the API key to the PageSpeed Insights and Chrome UX Report APIs so a leaked key is useless for anything else.

1 PageSpeed Insights skill

Deploy-caused SEO regressions: deploys, Core Web Vitals and Search Console

After each production deploy: the routes it changed, their lab speed, field Core Web Vitals, positions and index state, on one timeline, every morning.

SEODaily at 7:00, week summary on MondaysReport card

What agents do with PageSpeed Insights

One call does most of the work: GET https://www.googleapis.com/pagespeedonline/v5/runPagespeed?url=...&strategy=mobile&category=performance. The response has two halves. loadingExperience (and originLoadingExperience for the whole site) holds field data from the Chrome UX Report over the last 28 days: a 75th-percentile value and a FAST, AVERAGE or SLOW category for LARGEST_CONTENTFUL_PAINT_MS, INTERACTION_TO_NEXT_PAINT and CUMULATIVE_LAYOUT_SHIFT_SCORE. lighthouseResult holds a fresh lab run: categories.performance.score from 0 to 1, and audits such as largest-contentful-paint, total-blocking-time and cumulative-layout-shift with their numericValue. The CrUX API (records:queryRecord) and the CrUX History API return the same field metrics without running Lighthouse.

Teams schedule a weekly Core Web Vitals check of their top landing pages on mobile, an alert when a page drops from passing to failing, and a lab run on a few URLs after each deploy. Lab scores move from run to run, so careful skills test each URL more than once and report the median.

pagespeed.web.dev

Often used with PageSpeed Insights

Teams that use these

Your PageSpeed Insights numbers, on one board with everything else

Skills are free to use with any agent. Briefkin is where their results land: one board for every report, number and question your agents send, with a ping when something needs you.

Join the open beta Browse all skills

Free during the open beta. No card.