Raise a WordPress site's PageSpeed score with Zed

Raising a WordPress PageSpeed score with Zed means asking its agent panel to preview and then apply an xSpeed optimization pass through xSpeed Hub, confirming every tool call.

list_sitesget_score_historylist_modulesoptimize_sitegenerate_critical_csspurge_cacherun_speed_test

Last updated: October 2026

Example session · Zed

You: Using xSpeed Hub, raise the PageSpeed score on the studio site. Plan first.

list_sites read-only
→ 2 sites; studio is studio.example.com

optimize_site(site: studio, aggressiveness: standard, dry_run: true) dry run
→ plan: 4 settings to apply (CSS minify, defer JS, lazy-load images, compression), nothing changed

Zed: The plan is CSS minify, script deferral, lazy-loading and compression. Nothing has changed. Apply it to studio?

You: Yes, apply it.

optimize_site(site: studio, aggressiveness: standard) changes site
→ applied 3, undone 1 (broke the contact form), unfixable: 6 full-size photos

Zed: Three settings are on and one was undone because it broke the contact form. The full-size photos are on the unfixable list. Please open the home page and the contact page in a browser and check the console.

How Zed handles this

Zed asks before running an agent tool by default, and that suits this job. You open the agent panel and ask for a faster site. Zed asks to run list_sites, you allow it, and then it asks to run optimize_site with dry_run on. Allow that and you get the plan: which settings xSpeed would turn on at the standard level, in order, with nothing changed on the site. Because Zed prompts for reads as well as writes, expect a handful of prompts before any change.

Read the plan, then tell the agent to apply it. Zed prompts again, which is the useful moment: this is the call that changes the site. The pass applies each setting one at a time, checks that the page still renders after every change, and undoes anything that breaks it, taking up to two minutes per site. The result lists what was applied, what was undone and why, and what is unfixable. If you named a number, the agent can also pass target_score with up to three rounds, which needs the Pro plugin on the site.

When it finishes, the Hub gives the agent verify_urls and tells it to look at the pages before saying the pass went well. The plugin cannot run your JavaScript, so open those pages in a browser with the console visible. If the site has the Pro Critical CSS module, you can ask the agent to run generate_critical_css and then purge the cache so pages rebuild with it. Each of those calls gets its own prompt too.

Set up Zed once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Zed 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 remote server

Open Settings, then AI, then MCP Servers, click Add Server and choose Add Remote Server. Or run zed: open settings file and add the entry yourself. Zed calls MCP servers context servers, so the key is context_servers.

settings.json

{
  "context_servers": {
    "xspeedhub": {
      "url": "https://app.xspeedcache.com/xspeed/mcp"
    }
  }
}

3Sign in

Because the entry has no Authorization header, Zed prompts you to authenticate against the server with the standard MCP OAuth flow. Approve access on the xSpeed Hub page that opens. There is no token to paste. Back in Settings, AI, MCP Servers, a green dot beside xspeedhub with the tooltip Server is active means it is connected.

Text

Settings → AI → MCP Servers

1 / 3

Full Zed 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. The Zed agent confirms before it runs any tool action. The default setting, agent.tool_permissions.default, is confirm, and that covers MCP tool calls, reads included. A per-tool entry such as mcp:xspeedhub:get_cache_status with a default of allow lets that one tool run without a prompt, and the Always for tool button in the prompt writes the same entry. Setting the global default to allow auto-approves every tool, writes included, and then a write reaches the Hub as soon as your connection allows writes. xSpeed Hub has no confirmation step of its own.

What do I ask?

Three prompts written for Zed. More for this job are below.

Prompt for Zed

Use xSpeed Hub to preview an optimization for the studio site at the standard level. I will confirm each tool call.

Prompt for Zed

Apply the plan to studio with xSpeed Hub. Before you do, tell me what level it runs at.

Prompt for Zed

Summarize what the last xSpeed Hub run 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.

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.

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.

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.

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.

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.

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 Zed

Zed confirms every agent tool call by default, reads included, so a full run gives you several prompts. That is slower, but it is a real gate, and it is more than the Hub gives you, since the Hub runs a write as soon as your connection allows it. Resist the urge to set the global default to allow for the sake of speed. If the prompts bother you, add a per-tool allow entry for each read you trust, such as list_sites, because Zed documents no wildcard for MCP tools. The Always for tool button writes the same entry, so do not press it on optimize_site: the preview and the real pass are the same tool, and generate_critical_css and purge_cache should stay confirmed too.

More prompts for this job

They work in any client connected to xSpeed Hub.

Prompt

Ask xSpeed Hub to preview what optimize_site would change on shop with a safe pass. Do not apply anything.

Prompt

Use xSpeed Hub to optimize the blog site with the standard pass, then give me the pages to check by hand.

Prompt

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.

Prompt

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.

Prompt

Use xSpeed Hub to generate critical CSS for shop, then purge the cache so the pages are rebuilt with it.

Prompt

With xSpeed Hub, optimize shop, then compare the new PageSpeed score with the last stored one.

Prompt

Using xSpeed Hub, what could optimize_site not fix on the shop site?

Frequently asked questions

Zed confirms every agent tool call by default, including reads. That means an optimization run involves several prompts. You can add a per-tool allow entry for the reads you trust, but keep the write tools on a confirmation.

No. Confirmation gates the call, and the check covers the result. xSpeed verifies HTML only, so open the verify URLs in a browser with the console visible before you call the pass a success.

It measures the site, applies the recommended xSpeed settings one at a time, checks that the page still renders after each change, and undoes any change that breaks it. It then reports what was applied, skipped and reverted, and what it could not fix. It reaches caching and asset delivery only.

Yes, especially on a site you have not optimized before. dry_run: true returns the plan, what would be skipped and what cannot be fixed, and changes nothing. The tool description tells the agent to prefer it, but nothing forces it, so say so in your prompt if you want a preview.

Yes, with target_score, on a site that has xSpeed Pro. It repeats measure, apply and re-measure for up to 3 rounds per site and stops early when rounds stop helping, saying why. On a Free site the score target is ignored and you get a single pass with a note that no iterative tuner is installed.

That is a real answer. The settings it can apply were already enabled, so there was nothing to change. The result also lists what it could not fix, such as page weight, images hosted on another domain or DOM size, and those need changes outside a caching plugin.

The site checks its own HTML after each change and reverts anything that breaks it, but it cannot run JavaScript. After a run that changed something, the Hub tells the agent to open the returned verify_urls and check the page renders and the console is clean, or to give you the URLs to check yourself.

No. It needs the Pro Critical CSS module on that site, and without it the site answers with an unknown-tool error. On a Pro site, purge the cache afterwards, because pages already cached were built without the critical CSS.

Raise the PageSpeed score, from Zed.

xSpeed Hub is free and has no site cap. Connect your sites once and ask from the agent you already use.

Open xSpeed Hub Zed setup

Raise a WordPress site's PageSpeed score with Zed

How Zed handles this

Set up Zed once

What do I ask?

What happens, step by step

Reference

Rules worth keeping

More prompts for this job

Frequently asked questions

Keep going

Raise the PageSpeed score, from Zed.