How Muse handles this
The scores are easy to read from a phone. Ask Muse in WhatsApp or the Muse app for the stored PageSpeed history of the blog, and it calls get_score_history, which reads what the Hub already has and starts nothing. Muse replies with the trend in a line or two. The trouble starts with the natural next question: what would xSpeed change?
Muse calls optimize_site with dry_run on, and the Hub refuses. That surprises people, because a dry run changes nothing. The Hub still counts optimize_site as a write, so a connection token with Read-only everywhere on, which is how the Muse setup suggests you start, turns down the preview along with the real pass. You have two choices. Leave the token read-only and run the optimization later from a client at your desk, or switch Read-only everywhere off on the Connect AI page for this job, ask again, read the plan, approve the pass, and switch it back on when you are done.
With writes allowed, the pass runs as it would anywhere: each setting applied one at a time, the page checked after each, anything that breaks undone, for up to about two minutes. Muse reports applied, undone and unfixable in the thread. The verify step does not fit a phone well. The Hub gives Muse verify_urls and tells it to have the pages checked, and the honest answer is that someone should open them with a browser console, which means at a computer.
Set up Muse once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Muse 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.
2Copy 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)
3Ask 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 Muse 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. 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.
What do I ask?
Three prompts written for Muse. More for this job are below.
Use xSpeed Hub to read the stored PageSpeed history for blog. Do not run a new test.
With xSpeed Hub, preview an optimization for blog at the safe level and wait for my yes.
Using xSpeed Hub, tell me what the last optimization on blog applied, undid and could not fix, in three short lines.
What happens, step by step
optimize_site is the Hub tool for "make my site faster". It measures the site, applies the recommended xSpeed settings one at a time, checks the page still renders after each change, undoes anything that breaks it, and reports what it applied, what it undid and what it could not fix. It reaches caching and asset delivery only. Page weight, images hosted on another domain and heavy video are outside it, and the report says so instead of claiming a win.
01
See where the site stands
The agent reads get_score_history for the last stored scores and list_modules for which modules exist on that site and what state they are in. Neither changes anything.
02
Preview with dry_run
optimize_site with dry_run: true returns the plan: each change and its tier, what would be skipped (already on, or needing a higher aggressiveness) and what it cannot fix. Nothing is applied. The tool description tells the agent to prefer this before the first real run on a site you have not optimized before.
03
Apply it
optimize_site without dry_run applies the plan. aggressiveness is safe (removals and server-side changes only), standard (the default) or aggressive, which includes settings known to break some themes and should be opted into deliberately. A run can take up to about 2 minutes per site.
04
Look at the site afterwards
When changes were applied, the result carries verify_urls and a note. The site checks its own HTML and reverts anything that breaks it, but it cannot run JavaScript, so verified: true does not prove the page works in a browser. The Hub tells the agent to open those URLs and check the page renders and the console is clean, or to tell you which URLs to check.
05
Reach for a number only if you named one
target_score (1 to 100, Pro sites only) turns one pass into repeated rounds toward that score, up to max_rounds, with 3 as the most per site. Each round is a real PageSpeed measurement and up to about 2 minutes. The result says why it stopped, and diminishing returns means what is left is outside what caching can reach.
06
Critical CSS on Pro sites
generate_critical_css generates above-the-fold CSS so the first screen can paint without waiting for the full stylesheets. It needs the Pro Critical CSS module on that site, and the site answers with an unknown-tool error without it. Pages are rebuilt with it on their next build, so the agent purges the cache afterwards.
Reference
| Main tool | optimize_site (write): measure, apply one setting at a time, verify, undo what breaks, re-measure |
|---|---|
| Preview | dry_run: true returns the plan and changes nothing |
| aggressiveness | safe, standard (default) or aggressive |
| Every site at once | site: "all" or a list of handles, one result per site, sites run one after another; the Hub's confirm-once instruction does not name optimize_site, so your client's prompt is the gate |
| Time | Up to about 2 minutes per site |
| target_score | 1 to 100; needs Pro on the site; without it the site runs one pass and says so |
| max_rounds | Up to 3 per site; only sent along with target_score; 12 rounds in total per call |
| Wide fan-out with a target | Each site gets fewer rounds, and the result carries a note saying so |
| Result fields | applied, skipped, reverted, unfixable, score, verified, rounds; verify_urls after a run that changed something |
| Already tuned site | Returns "everything is already on" plus what it cannot fix; that is an answer, not a failure |
| Critical CSS | generate_critical_css (write), Pro Critical CSS module required; purge_cache afterwards |
| Read-only connection | optimize_site and generate_critical_css are refused; dry_run is still a write call, so it is refused too. Applies to the connection token with Read-only everywhere on and to a Viewer sign-in, not to other OAuth sign-ins |
Rules worth keeping
- Run dry_run first. optimize_site changes live site settings as soon as your connection allows writes. The tool description tells the agent to preview first on a site that has not been optimized, but that is guidance, so your client's approval prompt and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) are the real gates.
- Keep aggressive for a deliberate choice. It includes settings known to break some themes, and the agent should say so before using it.
- After a run that changed something, open the pages in verify_urls. The HTML checks cannot run JavaScript, so a page can pass them and still be broken in a browser. Do not call a run safe because verified is true.
- Relay the unfixable list. When a site is already tuned, the honest answer is that caching is done and the rest is page weight, hotlinked images or DOM size. The agent should not retry the tool or claim a gain it did not make.
- Only ask for target_score when you want the site driven to a number. Each round costs a real PageSpeed measurement, and a plain "make it faster" is one pass.
Good to know with Muse
Switching Read-only everywhere off is a change to the token, not to Muse, so for as long as it is off every client that sends that token can write, and a purge or a settings change runs as soon as one of them calls it, because xSpeed Hub has no confirmation step of its own. Turn it back on as soon as the pass is done. Meta says Muse will not take many important actions without your approval by default and lets you change when it asks in Settings, and its Sentinel agent checks what leaves its secure machine. Keep that approval on for this job, and read the plan before you answer yes. Muse is rolling out in the US first, and Meta does not review custom connectors.
More prompts for this job
They work in any client connected to xSpeed Hub.
Ask xSpeed Hub to preview what optimize_site would change on shop with a safe pass. Do not apply anything.
Use xSpeed Hub to optimize the blog site with the standard pass, then give me the pages to check by hand.
With xSpeed Hub, get docs to a mobile PageSpeed score of 90 if you can, and tell me why it stopped if it does not get there.
Use xSpeed Hub to show me what optimize_site would do on every site, as a dry run, and list which sites have the most left to change.
Use xSpeed Hub to generate critical CSS for shop, then purge the cache so the pages are rebuilt with it.
With xSpeed Hub, optimize shop, then compare the new PageSpeed score with the last stored one.
Using xSpeed Hub, what could optimize_site not fix on the shop site?
Frequently asked questions
Keep going
Raise the PageSpeed score with other agents
More with Muse
Documentation
- How to generate Critical CSS
- Performance recommendations
- How to run a speed test
- Free vs Pro: what is included
- How to write prompts for xSpeed Hub
- Muse + xSpeed
- Every AI agent that works with xSpeed
From the blog