# Raise a WordPress site's PageSpeed score with Antigravity

> Raising a WordPress PageSpeed score with Antigravity means asking its agent to preview and then apply an xSpeed optimization pass through xSpeed Hub, and then checking the pages it reports.

Page: https://xspeedcache.com/agent/antigravity/optimize-site/
Last updated: October 2026

In Antigravity you describe the job in the agent panel: make the news site faster, show me the plan first. The agent calls list_sites to find the handle and then optimize_site with dry_run on. The Hub previews the plan, which lists the settings xSpeed would turn on and the level it would use, and it changes nothing on the site. Antigravity runs MCP tools that have no rule in Ask mode, so that first call waits for your approval in a card before it executes.

If the plan reads well, tell the agent to apply it. The pass applies each setting one at a time, checks that the page still renders after every change, and undoes anything that breaks it. Expect up to two minutes per site. You get three lists back: applied, undone with the reason, and unfixable. The unfixable list is where an honest result lives, because page weight, hotlinked images and DOM size are beyond caching, and xSpeed reports them rather than claiming a win. A site that is already tuned says everything is already on.

The Hub then gives the agent a list of verify_urls and tells it to check the pages before it reports success. That matters because xSpeed checks the HTML in PHP and cannot run JavaScript, so a script change can leave valid HTML and a broken page. Open the listed URLs in a browser with the console visible, and report back what you find. If the site has the Pro Critical CSS module, ask the agent to generate it and purge the cache afterwards.

## Set up Antigravity once

### 1. Put 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.

### 2. Add xSpeed Hub to mcp_config.json

Antigravity reads ~/.gemini/config/mcp_config.json for every project, or .agents/mcp_config.json inside one workspace. In the IDE, open the ... menu at the top of the agent side panel, choose MCP Servers, then Manage MCP Servers and View raw config. Remote servers must use the serverUrl field; the older url and httpUrl fields are not supported.

File: `~/.gemini/config/mcp_config.json`

```json
{
  "mcpServers": {
    "xspeedhub": {
      "serverUrl": "https://app.xspeedcache.com/xspeed/mcp"
    }
  }
}
```

### 3. Authenticate

Open Agent settings with Cmd+, on macOS or Ctrl+, on Windows and Linux, go to the Customizations tab and click Authenticate next to xspeedhub. Sign in to xSpeed Hub in the browser and approve access, copy the authorization code the page shows, paste it into the settings panel and click Submit. Antigravity keeps the credentials it receives and refreshes them. In the CLI, type /mcp to open the MCP manager and check the server status.

```
Settings → Customizations → Authenticate
```

Full setup: https://xspeedcache.com/agent/antigravity/

### 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. Antigravity runs unconfigured MCP tools in Ask mode, so each call waits for your approval in a card before it executes. Allow rules such as mcp(xspeedhub/get_cache_status) or mcp(xspeedhub/*) let calls through without a prompt, Ask and Deny rules take precedence over Allow, and the Turbo permission preset allows MCP and web actions without asking. When you approve a card you can also edit its target to widen the grant. With Turbo or a broad allow rule, a write reaches the Hub as soon as your connection allows writes. xSpeed Hub has no confirmation step of its own.

## Prompts

- With xSpeed Hub, preview an optimization for the news site at the standard level. Stop after the plan.
- Apply the plan with xSpeed Hub, then give me the verify URLs and one thing to look for on each.
- Ask xSpeed Hub whether the news site has the Pro Critical CSS module. If it does, generate it and purge the cache. Ask me first.

## Example session

```
You: Make the news site faster with xSpeed Hub. Show me the plan first.
  → list_sites [read-only]: 5 sites; news is news.example.com
  → optimize_site(site: news, aggressiveness: standard, dry_run: true) [dry run]: plan: 5 settings to apply (CSS and JS minify, defer JS, lazy-load images, compression, browser cache), nothing changed
Agent: The plan has five steps: CSS and JavaScript minify, script deferral, lazy-loading, compression and browser caching. Nothing has changed. Apply it to news?
You: Yes, apply the plan.
  → optimize_site(site: news, aggressiveness: standard) [changes site]: applied 5, undone 0, unfixable: 4 ad scripts from other domains, large DOM
Agent: All five settings are on. The ad scripts and the large page structure are on the unfixable list, so the score may stay below your target. Open the home page and a long article in a browser and check the console.
```

## How it works

1. **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.
2. **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.
3. **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.
4. **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.
5. **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.
6. **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

- 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 Antigravity

Antigravity gates MCP tools with Deny, Ask and Allow lists, and Deny beats Ask beats Allow. A tool with no rule runs in Ask mode, but an allow rule such as mcp(xspeedhub/optimize_site) or mcp(xspeedhub/*) lets the preview and the real pass through without a card, and the Turbo permission preset allows MCP actions without asking. The Hub will not interrupt either way, because it runs a write as soon as your connection allows writes. When you approve a card you can edit its target to widen the grant, so leave the target on optimize_site rather than the whole server. If you use Turbo, add an Ask rule for optimize_site, generate_critical_css and purge_cache.

## 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

### Does Antigravity ask before it applies an xSpeed optimization?

Yes, by default. Antigravity runs unconfigured MCP tools in Ask mode, so each call waits for your approval, the dry run included. An allow rule for optimize_site or the Turbo preset removes the card for the real pass too, so keep an Ask rule on the write tools if you use either.

### Does an Antigravity optimization pass need a browser check afterwards?

Yes. xSpeed verifies the page HTML in PHP and cannot run JavaScript, so open the verify URLs the run returns, with the console visible, before you call the result good.

### What does optimize_site actually do?

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.

### Should I run a dry run first?

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.

### Can I tell it to get my site to a score of 90?

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.

### Why did it say everything is already on?

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.

### Does the agent check that my pages still work?

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.

### Does generate_critical_css work on a Free site?

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 with other agents

[Claude Code](https://xspeedcache.com/agent/claude-code/optimize-site/) · [Claude](https://xspeedcache.com/agent/claude/optimize-site/) · [Claude Cowork](https://xspeedcache.com/agent/claude-cowork/optimize-site/) · [ChatGPT](https://xspeedcache.com/agent/chatgpt/optimize-site/) · [Codex](https://xspeedcache.com/agent/codex/optimize-site/) · [Cursor](https://xspeedcache.com/agent/cursor/optimize-site/) · [GitHub Copilot in VS Code](https://xspeedcache.com/agent/github-copilot/optimize-site/) · [Windsurf](https://xspeedcache.com/agent/windsurf/optimize-site/) · [Gemini CLI](https://xspeedcache.com/agent/gemini-cli/optimize-site/) · [Zed](https://xspeedcache.com/agent/zed/optimize-site/) · [Kiro](https://xspeedcache.com/agent/kiro/optimize-site/) · [OpenCode](https://xspeedcache.com/agent/opencode/optimize-site/) · [OpenClaw](https://xspeedcache.com/agent/openclaw/optimize-site/) · [Hermes Agent](https://xspeedcache.com/agent/hermes-agent/optimize-site/) · [Grok Build](https://xspeedcache.com/agent/grok-build/optimize-site/) · [ChatGPT dots](https://xspeedcache.com/agent/chatgpt-dots/optimize-site/) · [Grok](https://xspeedcache.com/agent/grok/optimize-site/) · [Grok Bot](https://xspeedcache.com/agent/grok-bot/optimize-site/) · [Muse](https://xspeedcache.com/agent/muse/optimize-site/) · [Manus](https://xspeedcache.com/agent/manus/optimize-site/) · [Kimi Code](https://xspeedcache.com/agent/kimi/optimize-site/) · [Paperclip](https://xspeedcache.com/agent/paperclip/optimize-site/) · [NanoClaw](https://xspeedcache.com/agent/nanoclaw/optimize-site/)

## More with Antigravity

- [Purge the WordPress cache with Antigravity](https://xspeedcache.com/agent/antigravity/purge-cache/)
- [Find out why WordPress pages are not cached with Antigravity](https://xspeedcache.com/agent/antigravity/troubleshoot-cache/)
- [Scan a website for speed problems with Antigravity](https://xspeedcache.com/agent/antigravity/speed-scan/)
- [Run and track PageSpeed tests with Antigravity](https://xspeedcache.com/agent/antigravity/pagespeed-tests/)
- [Tune WordPress cache settings with Antigravity](https://xspeedcache.com/agent/antigravity/cache-settings/)
- [Warm the WordPress cache with Antigravity](https://xspeedcache.com/agent/antigravity/preload-cache/)
- [Set up the Redis object cache with Antigravity](https://xspeedcache.com/agent/antigravity/object-cache/)
- [Manage Cloudflare caching with Antigravity](https://xspeedcache.com/agent/antigravity/cloudflare/)
- [Manage every WordPress site at once with Antigravity](https://xspeedcache.com/agent/antigravity/fleet/)

## Documentation

- How to generate Critical CSS: https://xspeedcache.com/docs/critical-css/
- Performance recommendations: https://xspeedcache.com/docs/performance-recommendations/
- How to run a speed test: https://xspeedcache.com/docs/external-score/
- Free vs Pro: what is included: https://xspeedcache.com/docs/free-vs-pro/