Run and track PageSpeed tests with Claude Code

Tracking PageSpeed scores with Claude Code means asking it, in the terminal session that shipped a change, what your stored scores say and whether a fresh test through xSpeed Hub shows the change helped.

list_sitesget_score_historyrun_speed_testget_benchmark_historyrun_benchmark

Last updated: October 2026

Example session · Claude Code

You: Using xSpeed Hub, did Tuesday's deploy move the mobile score on shop?

get_score_history(site: shop) read-only
→ 4 stored runs; latest mobile 61 (3 days ago), previous 66; LCP 3.9 s against 3.2 s

Claude Code: The newest run, three days ago, is five points below the one before, and mobile LCP got slower. A fresh mobile test would confirm it. It takes up to two minutes and uses shared allowance. Run it?

You: Yes.

run_speed_test(site: shop, strategy: mobile) uses quota
→ mobile score 63, LCP 3.7 s, TBT 280 ms, saved to the Hub report history

Claude Code: Mobile is back near the earlier run, so the dip looks partly like noise. LCP is still above 3.2 s. I can run it again on desktop if you want a second reading.

How Claude Code handles this

The usual moment is right after a merge. You changed a theme template or switched on a module, the deploy finished, and you want to know whether PageSpeed moved. In Claude Code you stay in the session that made the change and ask something like: what was the last mobile score on shop, and is it different since Tuesday's deploy? Claude Code calls get_score_history through the xspeedhub server and reads back the stored runs: score, LCP, FCP, CLS, TBT, Speed Index and TTFB, for mobile and desktop.

If the newest run is older than your change, it says so and offers run_speed_test. That is a real PageSpeed Insights run started from the Hub, mobile or desktop, and it can take up to about two minutes, so the session waits on that one call. The Hub saves the result in its own report history, the Reports tab of the dashboard. get_score_history reads what the plugin stored on the site, so a Hub-run test may not show up in it, and Claude Code should compare like with like. When you want a cheaper signal first, run_benchmark times the home page cached and uncached. It returns response times only and never a Lighthouse score, and Claude Code should say so when you compare the two.

Because it is your terminal, the numbers can go straight into the pull request description or the commit message you are already writing. Nothing on the site changes during any of this. run_speed_test is classed as a write only because every run spends the shared speed-test allowance.

Set up Claude Code once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Claude Code guide.

1Put your sites in xSpeed Hub

Sign in at app.xspeedcache.com with Google or email; the Hub is free and has no site cap. Then connect each WordPress site from its own dashboard: click Connect Hub in the xSpeed Cache top bar, then Connect via xSpeed Hub. Each site needs the free xSpeed Cache plugin.

2Add xSpeed Hub to Claude Code

Run this once. --scope user makes the server available in every project; leave it off and it applies to the current project only, which is Claude Code's default.

Terminal

claude mcp add --transport http --scope user xspeedhub https://app.xspeedcache.com/xspeed/mcp

3Sign in with /mcp

Start Claude Code, run /mcp, pick xspeedhub and finish the sign-in in your browser. You approve access on an xSpeed Hub page; there is no token to paste, and Claude Code keeps the credentials it receives and refreshes them.

Text

/mcp

1 / 3

Full Claude Code setup, sign-in options and FAQ

Before you send a prompt that changes something

Reads change nothing on your sites, though contact_support emails xSpeed support. Writes run once your connection allows them, so your client's approval prompt and a read-only connection (the token's Read-only everywhere switch, or a Viewer sign-in) are the gates that matter. Claude Code asks before it runs an MCP tool unless a permission rule already allows it, or you work in auto mode, where a classifier reviews actions instead of you, or in bypassPermissions mode, which skips prompts. A rule such as mcp__xspeedhub__get_cache_status allows one tool, and mcp__xspeedhub__get_* allows every read whose name starts with get_. Keep purge_cache, update_settings, toggle_cache and the other write tools on the prompt, because the Hub itself runs a write as soon as your connection allows it.

What do I ask?

Three prompts written for Claude Code. More for this job are below.

Prompt for Claude Code

Using xSpeed Hub, what are the last three mobile scores on shop, and which metric moved most between them?

Prompt for Claude Code

I merged the font change an hour ago. Use xSpeed Hub to run a desktop test on blog and put the result next to the previous one for the PR description.

Prompt for Claude Code

With xSpeed Hub, time the home page cached and uncached on shop, then check the benchmark history to see if the new setting helped.

What happens, step by step

PageSpeed Insights is Google's Lighthouse audit, and its score and Core Web Vitals are the numbers most people mean by "my speed". Through xSpeed Hub an agent can read the scores a site has already stored, run a new PageSpeed test on mobile or desktop, and read or run a separate benchmark of cached against uncached response time. The three answer different questions, and the Hub tells the agent which to use for each.

Read before you test

get_score_history returns the stored PageSpeed Insights and GTmetrix runs for a site: the score per run, with LCP, FCP, CLS, TBT, Speed Index and TTFB, mobile and desktop. It starts nothing. The Hub tells the agent to use it whenever you ask what your score is, or whether it improved, because a new test spends a shared allowance.

Run a new test when you need one

run_speed_test runs a real PageSpeed Insights audit on the site from the Hub and returns the score, the Core Web Vitals and the top opportunities. strategy is mobile (the default) or desktop, and one call tests one of them. It can take up to about 2 minutes, so the agent should say it is running before it calls.

Test the other device

Mobile and desktop scores differ, often by a lot. For both, the agent makes two calls, one per strategy. A failure is reported with its reason: PageSpeed not configured, quota reached, a timeout, or a site the audit cannot reach.

Measure the cache on its own

run_benchmark times the home page with the cache bypassed and again served from cache, and returns the response times. It is a read tool, and it accepts site: "all" for every site. It does not return a Lighthouse score, so the agent must not use it to answer a PageSpeed question.

Compare over time

get_benchmark_history returns past benchmark runs, uncached against cached, together with the settings changes on the same timeline, which is how you answer "did that change help?". For PageSpeed scores over time, use get_score_history.

Reference

Read stored scores	get_score_history (read): PageSpeed Insights and GTmetrix runs, starts nothing
Metrics per run	Score, LCP, FCP, CLS, TBT, Speed Index, TTFB, for mobile and desktop
Run a new test	run_speed_test (write, uses the shared allowance): one PageSpeed Insights run per call
strategy	mobile (default) or desktop
Duration	Up to about 2 minutes per run
Why a test is a write	It spends a shared PageSpeed allowance and stores a report; it changes nothing on the site
Read-only access	A connection token with Read-only everywhere on, or a Viewer member's sign-in: run_speed_test is refused; get_score_history, run_benchmark and get_benchmark_history still work. An OAuth sign-in gets the scopes the client asks for
Benchmark	run_benchmark (read): cached against uncached response time for the home page, no Lighthouse score
Benchmark history	get_benchmark_history (read): past runs plus settings changes on the same timeline
Scheduling	The Hub does not schedule PageSpeed tests itself; its daily pass only reads reports the plugin already stored
Where a new test is stored	In the Hub's own report history, the one the Hub dashboard shows

Rules worth keeping

Check the history first. Ask for stored scores before starting a test, and run a new one only when you want a fresh measurement or something changed.
Never answer a PageSpeed or Lighthouse question with run_benchmark. It times your own cache and carries no score.
run_speed_test changes nothing on your site, but the Hub classes it a write because it spends a shared allowance. A connection token with Read-only everywhere on, or a Viewer sign-in, refuses it. An OAuth sign-in gets the scopes the client asks for, so there your client's approval prompt is the gate.
Lab scores move a few points between runs of the same page. The agent should compare like with like, same site, same strategy, and not report one run's difference as a trend.
A new test does not run on a timer. If you want a regular test, the agent has to be started by something else, such as a scheduled job in your client, and a scheduled run that spends the allowance should be one you are comfortable leaving unattended.

Good to know with Claude Code

Claude Code prompts for each MCP tool call unless a permission rule allows it. Auto mode, where a classifier reviews actions instead of you, and bypassPermissions mode, which asks nothing, skip the prompt too. A rule written as mcp__xspeedhub__* quietly includes run_speed_test, and a prompt like "retest after every edit" would then spend the shared allowance with no prompt in front of you. Allow the get_ tools with a narrower rule, leave run_speed_test on the prompt, and decide each time whether a two-minute test is worth it.

More prompts for this job

They work in any client connected to xSpeed Hub.

Prompt

Using xSpeed Hub, what is the mobile PageSpeed score for shop? Check the stored history before you run anything.

Prompt

Use xSpeed Hub to run a new mobile PageSpeed test on blog and tell me the score, LCP and the top opportunities.

Prompt

With xSpeed Hub, test shop on desktop and mobile and tell me which one is worse.

Prompt

Using xSpeed Hub, has the PageSpeed score on docs improved over the last few runs?

Prompt

Use xSpeed Hub to benchmark the cache on every site and tell me which one saves the least time.

Prompt

Did turning on minification on shop help? Use xSpeed Hub to compare the benchmark history around that change.

Prompt

My PageSpeed test failed on staging. Use xSpeed Hub to tell me why.

Frequently asked questions

Yes. It reads get_score_history for the stored runs, then calls run_speed_test for a fresh one and lines the two up by score, LCP, CLS and TBT. If the stored history has no run from before the deploy, it will say the comparison is thin rather than invent one.

No. run_speed_test does not touch the site. It is classed as a write tool because it spends the shared speed-test allowance, so a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) refuses it, and your Claude Code permission rules or permission mode decide whether it prompts.

run_speed_test runs a real PageSpeed Insights audit and returns a Lighthouse score with Core Web Vitals. run_benchmark measures how fast your own cache answers compared with an uncached request for the home page, and returns no Lighthouse score. Use the first for "what is my PageSpeed score" and the second for "is my caching working".

A single run can take up to about 2 minutes, so the agent should tell you it has started before it calls. One call tests one device, mobile or desktop, so checking both takes two calls.

Yes. get_score_history reads the stored PageSpeed Insights and GTmetrix runs for the site and starts nothing. The Hub tells the agent to read it first whenever you ask what your score is, because a new test spends a shared allowance.

No. The Hub does not schedule PageSpeed tests itself. Its daily pass re-verifies sites, snapshots cache status and pulls the PageSpeed and GTmetrix reports the plugin has already stored, and it can alert on a score regression. If you want regular new tests, they have to be started by a client that can run scheduled jobs.

It does not change your site. The Hub classes run_speed_test as a write because it spends a shared PageSpeed allowance and stores a report, and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) should not be able to cost the owner anything. Such a connection can still read stored scores with get_score_history.

Keep going

Track PageSpeed scores with other agents

More with Claude Code

Purge the cache Find out why pages are not cached Scan a site's speed Raise the PageSpeed score Tune cache settings Warm the cache Set up Redis object cache Manage Cloudflare Manage every site at once

Documentation

From the blog

Track PageSpeed scores, from Claude Code.

xSpeed Hub is free and has no site cap. Connect your sites once and ask from the agent you already use.

Open xSpeed Hub Claude Code setup