How Claude handles this
The conversation often starts with a report. You paste the lines a PageSpeed test gave you, or just say the blog loads slowly, and ask Claude what xSpeed can do about it. Claude looks up your sites, picks the one you meant, and calls optimize_site with dry_run on. You see a plan in the chat, written as plain steps: the settings it would turn on, one by one, and the level it chose. Nothing on the site has changed at this point.
You can argue with the plan before anything runs. Ask Claude to drop a step, to stay at the safe level, or to check list_modules first so it knows which modules the site has. When you are happy, say so and Claude calls optimize_site for real. The pass applies each setting one at a time, checks the page after each, and undoes what breaks it, which takes up to two minutes per site. You get the applied list, the undone list with reasons, and the unfixable list, which is the honest part: page weight and hotlinked images stay on it because caching cannot reach them.
The last step is the one a chat window hands back to you. The Hub tells the agent to open the verify URLs and check the page renders and the console is clean, or to tell you which URLs to check. Ask Claude for the list and open them in your browser. The plugin checks HTML only and cannot see JavaScript errors, so your eyes and the browser console are the real test.
Set up Claude once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Claude 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 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
3Connect 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 Claude 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. 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.
What do I ask?
Three prompts written for Claude. More for this job are below.
My blog scores badly on mobile. Using xSpeed Hub, show me what xSpeed would change, preview only, and explain each step.
Go ahead and apply that plan to the blog through xSpeed Hub, safe level only.
Which items on the xSpeed Hub unfixable list can I fix myself, and which need a developer?
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 Claude
The verify step falls to you. Ask Claude for the verify URLs and open each one in a browser with the developer console visible. The approval choice is per tool: Allow once covers one call, but Always allow on optimize_site covers the real pass as well as the preview, and a tool set to Always allow under Customize, Connectors runs as soon as your connection allows writes. Keep optimize_site on Needs approval. Anthropic notes that Research can call connector tools without further approval, so block optimize_site and the other write tools before you use Research with this connector. On a Team or Enterprise plan an Owner adds xSpeed Hub for the organization, and each member then connects with their own account.
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 Claude
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
- Claude + xSpeed
- Every AI agent that works with xSpeed
From the blog