How Kiro handles this
You finished a task in Kiro that touched how a theme loads its assets, and the follow-up is to check what that did to PageSpeed. Ask the agent for the site's score history. It calls get_score_history through the Hub and returns the stored runs, with score, LCP, FCP, CLS, TBT, Speed Index and TTFB for mobile and desktop. It can set those against the task you just closed, so the answer reads as a before and after rather than a bare list.
When the stored runs are too old to say anything, ask for run_speed_test, a PageSpeed Insights run from the Hub, mobile or desktop, up to about two minutes. The Hub keeps the result in its own report history, while get_score_history reads the plugin's stored runs, so the two can differ. run_benchmark gives a quicker read on the home page cached and uncached, with no Lighthouse score, and get_benchmark_history shows the earlier runs against your settings changes.
Kiro prompts for an MCP tool unless the tool is on the server's autoApprove list. That list suits this job well. Read tools such as get_score_history, get_benchmark_history and run_benchmark can go on it, so your reviews are not interrupted. A permissions rule that matches xspeedhub/get_* with the effect allow does the same for every read whose name starts with get_. The one tool that starts something, run_speed_test, can stay off, so you see each test before it runs and decide whether the answer is worth the wait. Each call tests one device, mobile or desktop, so a full check is two tests.
Set up Kiro once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Kiro 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 mcp.json
Open the command palette and run Kiro: Open user MCP config (JSON), then add this entry. The user file applies in every workspace. A project can carry its own .kiro/settings/mcp.json instead, but Kiro does not load a workspace's MCP config until you trust that workspace. Kiro reconnects servers when you save the file.
{
"mcpServers": {
"xspeedhub": {
"url": "https://app.xspeedcache.com/xspeed/mcp"
}
}
} 3Approve access in the browser
After you save, Kiro opens the xSpeed Hub authorization page. It registers itself through dynamic client registration, so there is no client ID to create. Sign in to the Hub, approve, and check the MCP servers tab in the Kiro panel for a connected xspeedhub. There is no token to paste; Kiro keeps the credentials it receives.
Full Kiro 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. Kiro prompts before it runs an MCP tool unless a rule allows it. Rules live in two places: autoApprove in the server's mcp.json entry, which lists tool names, and mcp rules in permissions.yaml, such as a match of xspeedhub/get_* with effect allow. Allow the reads and keep purge_cache, update_settings, toggle_cache and the other write tools off both lists, because the Hub itself runs a write as soon as your connection allows it. Putting "*" in autoApprove skips the prompt for every Hub tool, writes included. In a workspace you have not trusted, Kiro asks before every MCP call even when autoApprove lists the tool.
What do I ask?
Three prompts written for Kiro. More for this job are below.
Use xSpeed Hub to read the PageSpeed history for shop and tell me whether the asset change from my last task shows up.
With xSpeed Hub, run a mobile test on blog and compare it with the last stored mobile run.
Ask xSpeed Hub for the benchmark history on shop and mark the points where I changed settings.
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.
01
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.
02
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.
03
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.
04
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.
05
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 Kiro
The autoApprove list works per tool, which is the useful part. If you put an asterisk in it, or add run_speed_test by habit, Kiro stops prompting for it and every later test spends the shared speed-test allowance without you seeing it. Keep the get_ tools and run_benchmark on the list and leave run_speed_test off. In a workspace you have not trusted, Kiro asks before every MCP call even when autoApprove lists the tool.
More prompts for this job
They work in any client connected to xSpeed Hub.
Using xSpeed Hub, what is the mobile PageSpeed score for shop? Check the stored history before you run anything.
Use xSpeed Hub to run a new mobile PageSpeed test on blog and tell me the score, LCP and the top opportunities.
With xSpeed Hub, test shop on desktop and mobile and tell me which one is worse.
Using xSpeed Hub, has the PageSpeed score on docs improved over the last few runs?
Use xSpeed Hub to benchmark the cache on every site and tell me which one saves the least time.
Did turning on minification on shop help? Use xSpeed Hub to compare the benchmark history around that change.
My PageSpeed test failed on staging. Use xSpeed Hub to tell me why.
Frequently asked questions
Keep going
Track PageSpeed scores with other agents
More with Kiro
Documentation
- How to run a speed test
- PageSpeed Insights integration
- Running speed tests in xSpeed Hub
- How to run a PageSpeed audit
- How to write prompts for xSpeed Hub
- Kiro + xSpeed
- Every AI agent that works with xSpeed
From the blog
- Reading a PageSpeed Report in 2026: 30% of the Score Is a Metric Google Does Not Rank You On
- 45% of the WordPress Sites Our Scan Calls Clean Are Failing Google in 2026: Lab Scores Against Field Data
- The Same Page Scored 61 and 73 Twelve Minutes Apart: How to Benchmark WordPress Caching Plugins in 2026