# Run and track PageSpeed tests with Muse

> Tracking PageSpeed scores with Muse means messaging Meta's personal agent, from its app, muse.ai or WhatsApp, for your sites' stored PageSpeed history through an xSpeed Hub custom connector, and testing afresh only when your token allows writes.

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

Muse is where you ask on the move. You are away from your desk, a client sends a screenshot of a slow page, and you want the numbers before you reply. In a Muse thread, in the app or in WhatsApp, you ask how the site scores. Muse calls get_score_history through the custom connector you asked it to create, and answers from the stored runs: score, LCP, FCP, CLS, TBT, Speed Index and TTFB, for mobile and desktop. Ask for two or three short lines, because a phone screen does not suit a seven-column table.

That read starts nothing on the site. A fresh reading is run_speed_test, a PageSpeed Insights run from the Hub, mobile or desktop, which can take up to about two minutes. The Hub classes it a write because it spends a shared allowance, and it saves the result in its own report history on the Reports tab, so a later history read may not show it. run_benchmark is the quicker check on whether caching works at all: it times the home page cached and uncached and has no Lighthouse score.

How the connector was set up decides which of those Muse can call. The credential is the Hub's connection token, kept in Muse's Secure Credentials Store, and the token has a Read-only everywhere switch. With it on, get_score_history, get_benchmark_history and run_benchmark answer normally and run_speed_test is refused with a message saying the connection is read-only. For most PageSpeed questions asked from a phone, reading is all you need.

## Set up Muse 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. Copy the connection token from xSpeed Hub

Sign in at app.xspeedcache.com as the workspace owner and open Connect AI. Copy the connection token. For a first try, turn on Read-only everywhere: the Hub then refuses every write tool on that token, so Muse can read but not purge or change settings.

```
xSpeed Hub  >  Connect AI  >  connection token (Read-only everywhere: on)
```

### 3. Ask Muse to create a custom connector

Send this message to Muse in the app, on muse.ai or in WhatsApp, and follow the steps Muse gives you. When it asks for the credential, give it the token as a Bearer token. Meta does not review custom connectors, so only finish this for the request you started yourself.

```
Create a custom connector called xSpeed Hub for the MCP server at
https://app.xspeedcache.com/xspeed/mcp
It authenticates with a Bearer token in the Authorization header. Once it is connected, use xSpeed Hub to list my sites.
```

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

### 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. Meta says Muse will not take many important actions without your approval by default, that many connectors can be set up to only retrieve data, and that you change when Muse asks for approval in its Settings. Muse's separate Sentinel agent also decides what leaves its secure machine and asks you for permission when needed. xSpeed Hub has no confirmation step of its own, so a write runs as soon as Muse calls it and your connection allows writes. The firm stop here is the token: with Read-only everywhere on, the Hub refuses every write tool, whatever Muse decides. Turn it off only when you want Muse to purge or change settings, and read each question Muse asks before you answer yes.

## Prompts

- Using xSpeed Hub, how does shop score on PageSpeed right now? Give me mobile and desktop in two lines.
- Ask xSpeed Hub for the PageSpeed history of blog and tell me whether mobile went up or down this month.
- Use xSpeed Hub to time shop cached and uncached, and tell me why that is not a PageSpeed score.

## Example session

```
You: Using xSpeed Hub, how does shop score on PageSpeed? A client says it feels slow on phones.
  → get_score_history(site: shop) [read-only]: latest mobile 49 (8 days ago), desktop 81; mobile LCP 4.6 s, TBT 420 ms
Agent: Mobile is 49 and desktop 81, from a run eight days ago. On phones the slow parts are LCP at 4.6 s and TBT at 420 ms. Want a fresh mobile test? It takes up to two minutes.
You: Yes, run one.
  → run_speed_test(site: shop, strategy: mobile) [uses quota]: This connection is read-only; write tools are not permitted.
Agent: The Hub refused the test because this connector uses a read-only token, so nothing ran and no allowance was spent. The stored run is the latest reading I can give you. To allow tests, turn off Read-only everywhere on the token in the Hub, which also allows purges and settings changes.
```

## 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 Muse

Meta says Muse will not take many important actions without your approval by default and that you can change when it asks in its Settings, and its Sentinel agent checks what leaves Muse's secure machine. Neither is an xSpeed control, and xSpeed Hub has no confirmation step of its own, so with a write-enabled token run_speed_test runs as soon as Muse calls it. Meta's pages describe no scheduled tasks for Muse, so it will not track scores on a timer; each check is one you start in a thread. If you turn Read-only everywhere off to allow tests, the same token then allows purges and settings changes too, because the switch covers every write tool at once. Muse is rolling out in the US first, and Meta does not review custom connectors, so create this one only from a request you sent yourself.

## 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 Muse check my PageSpeed score from WhatsApp?

Yes, wherever you message Muse: the Muse app, muse.ai or WhatsApp. It reads the stored history with get_score_history and answers in the thread. Muse is rolling out in the US first, so access depends on your account.

### Why did Muse say the speed test was refused?

The connection token has Read-only everywhere turned on, so the Hub refuses every write tool, and run_speed_test counts as one because it spends a shared allowance. Reading stored scores still works. Turning the switch off allows tests, and every other write as well.

### 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](https://xspeedcache.com/agent/claude/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/) · [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 Muse

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