How Manus handles this
Manus suits the version of this job that spans several sites. You write one task: use xSpeed Hub to preview an optimization on every site, rank them by how much each plan would change, and wait for me. Manus calls optimize_site once for every site with dry_run on, which returns a plan per site and changes nothing on any of them, and turns the results into a short ranked table.
The table is the useful part. One site has five settings left to turn on, another two, and a third answers that everything is already on, which is a finished answer and not a failure to retry. You pick the site with the most to gain and tell Manus to apply its plan. That real pass measures the site, applies each setting one at a time, checks the page after each, and undoes what breaks it, taking up to about two minutes. Manus adds applied, undone and unfixable to its report, along with the verify URLs.
Manus describes no per-tool approval setting for a custom MCP server, so the wait for me in your task is what keeps the preview and the pass apart. Write it plainly. The Hub's confirm-once instruction for writes across every site names purges, toggles, settings and preloader changes, not optimize_site, so the model has no Hub instruction to stop before a fleet-wide pass. If you want the real pass on several sites at once, name them and approve that list yourself.
Set up Manus once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Manus 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, open Connect AI and copy the connection token. If Manus will only report, turn on Read-only everywhere so the Hub refuses every write tool on that token.
xSpeed Hub > Connect AI > connection token
3Add xSpeed Hub as a custom MCP server
In Manus, open Settings, then Integrations, then Custom MCP Servers, and click Add Server. Name it xSpeed Hub, enter this as the server URL, and enter the connection token as the Bearer token in the authentication field.
https://app.xspeedcache.com/xspeed/mcp
4Let Manus test it, then name it in a task
Manus checks that it can reach the server and read its list of tools. Then start a task that names xSpeed Hub, so Manus uses this server.
Use xSpeed Hub to list my sites and tell me which ones have page caching turned off.
Full Manus 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. Manus's custom MCP documentation describes no per-tool approval setting for a custom server, and its scheduled tasks offer a skip confirmations option that lets Manus act without asking each time. xSpeed Hub has no confirmation step of its own, so a write runs as soon as Manus calls it and your connection allows writes. The Hub tells the agent to confirm the target site and to ask once before a write that touches every site, but that is an instruction. The firm stop is the token: with Read-only everywhere on, the Hub refuses every write tool. Keep it on for scheduled work, and leave skip confirmations off for any task that may write.
What do I ask?
Three prompts written for Manus. More for this job are below.
Use xSpeed Hub to preview an optimization on every site as one dry run, rank them by how much each would change, and wait for me.
With xSpeed Hub, apply the plan to shop only, then add the verify URLs and the unfixable list to the report.
Every Monday, use xSpeed Hub to read the stored PageSpeed history for each site and report any drop. Report only.
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 Manus
A connection token with Read-only everywhere on refuses optimize_site entirely, including the dry run, because the Hub counts it as a write. So this job needs the switch off, and while it is off nothing in Manus or the Hub stops a real pass once the model decides to send one: xSpeed Hub has no confirmation step of its own. The switch belongs to the token, not to one task, so it also covers every scheduled task that sends the same token. Keep the instruction to wait in every task, keep optimize_site out of scheduled tasks, leave skip confirmations off, and turn Read-only everywhere back on when the pass is done. The verify step is yours too. Open the verify URLs in a browser with the console visible, because the plugin cannot run JavaScript.
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 Manus
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
- Manus + xSpeed
- Every AI agent that works with xSpeed
From the blog