How Gemini CLI handles this
You are in a terminal on a spare afternoon and want a quick read on a site. Gemini CLI lists your Hub sites, calls get_score_history for the one you named and prints the stored runs: score, LCP, FCP, CLS, TBT, Speed Index and TTFB, mobile and desktop. Because it is a terminal tool, you can ask for the output in a form that suits the next step, a small table, a list of the three slowest metrics, or one sentence per device.
For a new reading it calls run_speed_test, a PageSpeed Insights run from the Hub, mobile or desktop, which takes up to about two minutes. The result goes to the Hub's own report history, on the Reports tab, and may not appear in what get_score_history reads from the plugin. run_benchmark is the quick sibling: it times the home page cached and uncached from the Hub and returns no Lighthouse score. When you ask for a comparison, tell Gemini CLI which of the two you mean, so a response time is not set against a score.
Gemini CLI asks before a tool call unless the server has been marked as trusted or you started it with --approval-mode=yolo (or --yolo), so you normally see each call before it runs. That is a good fit for this job, because the read calls are harmless and the one test is something you want to start deliberately. Paste a result into a ticket or a chat when you are done.
Set up Gemini CLI once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Gemini CLI 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 Gemini CLI
Run this once. --scope user writes the server to ~/.gemini/settings.json so it works in every project; without it Gemini CLI saves to the project's .gemini/settings.json, which is the default.
gemini mcp add --scope user --transport http xspeedhub https://app.xspeedcache.com/xspeed/mcp
3Authenticate with /mcp auth
Start gemini and run /mcp auth xspeedhub. A browser page opens where you sign in to xSpeed Hub and approve access, and Gemini CLI receives the redirect on a local port. There is no token to paste, and the client keeps the credentials it receives. Run /mcp afterwards to check that xspeedhub shows as connected and lists its tools.
/mcp auth xspeedhub
Full Gemini CLI 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. Gemini CLI shows a confirmation for an MCP tool call unless the server entry sets trust to true or you start Gemini CLI with --approval-mode=yolo (or --yolo), which approves every tool call. You can proceed once, always allow that tool, always allow the whole xspeedhub server, or cancel; the last two choices stop later prompts for those tools. Policy rules in ~/.gemini/policies can allow, deny or ask for a named tool by server and tool name. The Hub has no confirmation step of its own, so a trusted server, YOLO mode or an allow rule lets a write run as soon as your connection allows writes.
What do I ask?
Three prompts written for Gemini CLI. More for this job are below.
Use xSpeed Hub to list my sites, then print the last mobile and desktop score for each as a table.
With xSpeed Hub, run a desktop test on blog and tell me how it differs from the previous stored desktop run.
Ask xSpeed Hub for the benchmark history on shop and say if cached response time got better after my last change.
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 Gemini CLI
Gemini CLI skips its tool prompts for a server that has trust set, and starting it with --approval-mode=yolo (or --yolo) approves every tool call. If you set trust on the xspeedhub server so reads run quickly, run_speed_test stops prompting as well, and every test it starts spends the shared speed-test allowance. Choosing always allow for the whole server in a prompt has the same effect for every tool. Leave trust off for this server, do not start Gemini CLI in yolo mode, choose always allow for get_score_history alone, and approve the one test call each time it appears.
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 Gemini CLI
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
- Gemini CLI + 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