# Run and track PageSpeed tests with Claude

> Tracking PageSpeed scores in Claude means chatting with it about a site's Lighthouse history and asking for a fresh test, using the xSpeed Hub connector you added to your Claude account.

Page: https://xspeedcache.com/agent/claude/pagespeed-tests/
Last updated: October 2026

This is the conversation you have before a client call or at the end of the month: how is the site doing on PageSpeed, and is it better than last time? In the Claude chat you ask in plain words and name the site. Claude reads the stored history with get_score_history and answers with a short table: mobile and desktop score, LCP, CLS and TBT for each run, newest first, with a sentence on what changed.

When the history is thin or old, say "run a new desktop test on blog". Claude calls run_speed_test, which asks Google's PageSpeed Insights for a fresh Lighthouse run from the Hub. It can take up to about two minutes, and the chat simply waits. You can follow with a request to time the home page cached and uncached, which runs run_benchmark. That tool measures response time only, so Claude should tell you there is no score to compare it with.

Because the answer lands in a chat window, it is easy to lift into an email or a status report. Ask for the figures in plain language with one line on what each metric means for a reader who is not technical, and tell Claude to quote the numbers from the tool results instead of rounding them into a verdict. A test you start is saved to the Hub's own report history, the Reports tab of the dashboard, while get_score_history reads the plugin's stored runs, so a fresh run may be missing from the next history question. One call tests one device, so ask for mobile and desktop as two runs.

## Set up Claude once

### 1. Put 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.

### 2. Add xSpeed Hub as a custom connector

Go to Customize > Connectors and click Add custom connector. Name it xspeedhub and paste the URL. Under Authentication choose Sign in now, and if Claude asks how it identifies itself, choose Register automatically, which uses dynamic client registration. Click Add. On a Team or Enterprise plan an Owner does this under Organization settings > Connectors, with Add, then Custom, then Web.

```
https://app.xspeedcache.com/xspeed/mcp
```

### 3. Connect and turn it on in a chat

Click Connect on the xspeedhub connector and approve access on the xSpeed Hub page that opens. Then, in a conversation, click + in the message box, choose Connectors and switch xspeedhub on. Claude can use the connector only in conversations where that toggle is on.

```
+  >  Connectors  >  xspeedhub (on)
```

Full setup: https://xspeedcache.com/agent/claude/

### 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 can ask for your approval before it uses a connector tool. Allow once runs that call, and Always allow skips the prompt for that tool from then on. Under Customize > Connectors you can set each tool, or a group of tools, to Always allow, Needs approval or Blocked. xSpeed Hub has no confirmation step of its own, so a write tool you set to Always allow runs as soon as your connection allows writes. Keep purge_cache, update_settings, toggle_cache and the other write tools on Needs approval, block the ones you never want. For read-only access, sign in as a Viewer member of the workspace, or use the connection token with Read-only everywhere on, which needs the Request headers beta. The switch does not apply to a normal OAuth sign-in.

## Prompts

- Ask xSpeed Hub for the PageSpeed history of my blog site and show it as a table, newest first, mobile and desktop.
- Using xSpeed Hub, is the desktop score on shop better than a month ago? Say which metric explains the difference.
- Use xSpeed Hub to run a fresh mobile test on docs, then write two sentences I can paste into an update for the client.

## Example session

```
You: Using xSpeed Hub, how is the blog doing on PageSpeed compared with last month?
  → get_score_history(site: blog) [read-only]: 6 stored runs; mobile 54, 57, 59; desktop 81, 83, 84; most recent 5 days ago
Agent: Both devices crept up over the three runs on each. Mobile gained five points, desktop three. The newest run is five days old. Want a fresh mobile test? It can take up to two minutes.
You: Go ahead.
  → run_speed_test(site: blog, strategy: mobile) [uses quota]: mobile score 60, LCP 3.4 s, CLS 0.02, saved to the Hub report history
Agent: Mobile is 60 now, one point above the last stored run. CLS is low, and LCP is the number to watch.
```

## How it works

1. **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.
2. **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.
3. **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.
4. **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.
5. **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

- 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

Claude can ask before it uses a connector tool, with Allow once and Always allow on the prompt, and under Customize > Connectors you can set each tool to Always allow, Needs approval or Blocked. Always allow is sensible for get_score_history, which only reads. Keep run_speed_test on Needs approval. Each run spends the shared speed-test allowance, and Always allow means any later chat that mentions testing can start one without stopping to ask you. Anthropic notes that Research can call connector tools without further approval, so set run_speed_test to Blocked before you use Research with this connector. The connector also has to be switched on from the plus menu in each chat before Claude can call it.

## 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

### Can I ask Claude for my PageSpeed score without running a test?

Yes. Claude reads get_score_history, which returns what was already measured and starts nothing. It only calls run_speed_test when you ask for a new measurement or when the stored runs are older than your change.

### Why does a test in Claude take so long?

run_speed_test asks PageSpeed Insights for a real Lighthouse run, which can take up to about two minutes. Claude waits for it to finish. A cached-versus-uncached timing from run_benchmark is much quicker, but it gives no Lighthouse score.

### What is the difference between run_speed_test and run_benchmark?

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".

### How long does a PageSpeed test take?

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.

### Can I ask for the last score without running a new test?

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.

### Will the Hub run PageSpeed tests on a schedule?

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.

### Why is a speed test treated as a write tool?

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.

## Track PageSpeed scores with other agents

[Claude Code](https://xspeedcache.com/agent/claude-code/pagespeed-tests/) · [Claude Cowork](https://xspeedcache.com/agent/claude-cowork/pagespeed-tests/) · [ChatGPT](https://xspeedcache.com/agent/chatgpt/pagespeed-tests/) · [Codex](https://xspeedcache.com/agent/codex/pagespeed-tests/) · [Cursor](https://xspeedcache.com/agent/cursor/pagespeed-tests/) · [GitHub Copilot in VS Code](https://xspeedcache.com/agent/github-copilot/pagespeed-tests/) · [Windsurf](https://xspeedcache.com/agent/windsurf/pagespeed-tests/) · [Gemini CLI](https://xspeedcache.com/agent/gemini-cli/pagespeed-tests/) · [Antigravity](https://xspeedcache.com/agent/antigravity/pagespeed-tests/) · [Zed](https://xspeedcache.com/agent/zed/pagespeed-tests/) · [Kiro](https://xspeedcache.com/agent/kiro/pagespeed-tests/) · [OpenCode](https://xspeedcache.com/agent/opencode/pagespeed-tests/) · [OpenClaw](https://xspeedcache.com/agent/openclaw/pagespeed-tests/) · [Hermes Agent](https://xspeedcache.com/agent/hermes-agent/pagespeed-tests/) · [Grok Build](https://xspeedcache.com/agent/grok-build/pagespeed-tests/) · [ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/pagespeed-tests/) · [Grok](https://xspeedcache.com/agent/grok/pagespeed-tests/) · [Grok Bot](https://xspeedcache.com/agent/grok-bot/pagespeed-tests/) · [Muse](https://xspeedcache.com/agent/muse/pagespeed-tests/) · [Manus](https://xspeedcache.com/agent/manus/pagespeed-tests/) · [Kimi Code](https://xspeedcache.com/agent/kimi/pagespeed-tests/) · [Paperclip](https://xspeedcache.com/agent/paperclip/pagespeed-tests/) · [NanoClaw](https://xspeedcache.com/agent/nanoclaw/pagespeed-tests/)

## More with Claude

- [Purge the WordPress cache with Claude](https://xspeedcache.com/agent/claude/purge-cache/)
- [Find out why WordPress pages are not cached with Claude](https://xspeedcache.com/agent/claude/troubleshoot-cache/)
- [Scan a website for speed problems with Claude](https://xspeedcache.com/agent/claude/speed-scan/)
- [Raise a WordPress site's PageSpeed score with Claude](https://xspeedcache.com/agent/claude/optimize-site/)
- [Tune WordPress cache settings with Claude](https://xspeedcache.com/agent/claude/cache-settings/)
- [Warm the WordPress cache with Claude](https://xspeedcache.com/agent/claude/preload-cache/)
- [Set up the Redis object cache with Claude](https://xspeedcache.com/agent/claude/object-cache/)
- [Manage Cloudflare caching with Claude](https://xspeedcache.com/agent/claude/cloudflare/)
- [Manage every WordPress site at once with Claude](https://xspeedcache.com/agent/claude/fleet/)

## Documentation

- How to run a speed test: https://xspeedcache.com/docs/external-score/
- PageSpeed Insights integration: https://xspeedcache.com/docs/pagespeed-insights-integration/
- Running speed tests in xSpeed Hub: https://xspeedcache.com/docs/hub-speed-tests-and-notifications/
- How to run a PageSpeed audit: https://xspeedcache.com/docs/pagespeed/