How Grok handles this
You have a number in mind. A client wants the landing site at 90 on mobile, and you ask Grok on grok.com whether xSpeed can get it there. Grok first reads list_modules, which shows whether the site runs xSpeed Pro, because a target score only works on a Pro site; on a Free site the target is ignored and you get a single pass with a note. Then it calls optimize_site with dry_run on and shows you the plan, and nothing on the site changes.
When you say go, Grok calls optimize_site with target_score 90 and max_rounds 2. Each round is a real PageSpeed measurement and can take up to about two minutes, so the run is slower than a single pass. The result says how many settings were applied and undone, the score it reached and why it stopped. Here it stops at 86 with diminishing returns, which means what is left is outside what caching can reach, and the unfixable list says what: a hero video and a third-party chat widget. Grok's job at that point is to say so plainly, not to try again or promise the last four points.
The verify step is yours. The Hub gives Grok verify_urls after a run that changed something and tells it to have the pages checked. Ask for the list in the chat and open each page with the browser console visible, because xSpeed checks HTML and cannot run JavaScript. If a page is broken, tell Grok which one and what you saw, so it can say which setting most likely caused it.
Set up Grok once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Grok 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 grok.com/connectors, click New Connector and select Custom. Enter this as the MCP server URL and complete the authentication: approve access on the xSpeed Hub page that opens. Grok then reads the Hub's tools and makes them available in your conversations.
https://app.xspeedcache.com/xspeed/mcp
3Ask a first question
Start a chat and ask something that names xSpeed Hub, so Grok reaches for the connector. A list of your sites with their cache status means the connection works.
Use xSpeed Hub to list my sites and tell me which ones have page caching turned off.
Full Grok 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. xAI's connector documentation describes no per-tool approval setting. It says Grok can use a connector's tools whenever your questions relate to that service. xSpeed Hub has no confirmation step of its own, so a purge or a settings change runs as soon as Grok 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, not a lock. If you want Grok to read and never change anything, sign in as a Viewer member of the workspace, which only ever gets read access. Otherwise read what Grok says it is about to do before you answer yes.
What do I ask?
Three prompts written for Grok. More for this job are below.
Use xSpeed Hub to get landing to 90 on mobile if it can. Show me the plan and wait for my yes.
With xSpeed Hub, check whether landing runs xSpeed Pro before you try a target score.
Using xSpeed Hub, why did the last optimization on landing stop short of the target?
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 Grok
xAI's connector documentation describes no per-tool approval setting, and it says Grok can use a connector's tools whenever your question relates to the service. So the pause between the preview and the real pass in this chat is the model choosing to ask, not a gate. xSpeed Hub has no confirmation step of its own, and the real pass runs as soon as Grok sends it on a connection that allows writes. Say in your message that you want the plan first and that Grok must wait for your yes. If you want Grok to look at scores with no chance of a change, sign in as a Viewer member of the workspace; the Hub then refuses optimize_site entirely, dry run included, while get_score_history and list_modules keep working. A target score spends real PageSpeed measurements, so name one only when you mean it.
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 Grok
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
- Grok + xSpeed
- Every AI agent that works with xSpeed
From the blog