# Run and track PageSpeed tests with Cursor

> Tracking PageSpeed scores with Cursor means asking its agent, in the editor where you edit the theme, for stored scores and a fresh test of the live site through xSpeed Hub.

Page: https://xspeedcache.com/agent/cursor/pagespeed-tests/
Last updated: October 2026

You are halfway through a theme edit, a font swap or a script cleanup, with the file open next to the chat panel. The question is whether any of it shows up on PageSpeed. In Cursor you ask the agent for the history of the site, and it calls get_score_history to read the stored runs, with score, LCP, FCP, CLS, TBT, Speed Index and TTFB for mobile and desktop. The answer sits beside the code you just changed, which makes it easy to connect a metric to an edit.

After you deploy, run_speed_test gives a fresh PageSpeed Insights reading from the Hub, mobile or desktop, in up to about two minutes. It measures the live site, so an edit that is still only in your editor will not show up. For a faster signal, run_benchmark times the home page cached and uncached and returns no Lighthouse score. Ask Cursor to say which of the two it used each time, so you do not read a response time as a score.

Whether Cursor asks before it uses an MCP tool depends on your Run Mode, set under Settings, Agents, Approvals and Execution. Allowlist runs only what you listed and asks about the rest. Auto-review, the recommended default since Cursor 3.6, runs allowlisted calls and sends the rest to a classifier instead of to you. Run Everything asks nothing. When it does ask, you can expand the call to see its arguments. For this job that choice matters more than the connection itself. Know where results land, too. A run_speed_test result is saved to the Hub's own report history on the dashboard's Reports tab, and get_score_history reads the plugin's stored runs, so the two lists can differ. One call tests one device.

## Set up Cursor 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.json

Add the server to ~/.cursor/mcp.json to have it in every project, or to .cursor/mcp.json inside a project to scope it there. The entry is just a name and a url.

File: `~/.cursor/mcp.json`

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

### 3. Enable it and sign in

Open Customize in the sidebar, find xspeedhub and make sure it is switched on. When Cursor starts the OAuth sign-in, approve access on the xSpeed Hub page. There is no token to paste. If the server shows an error, open the Output panel with Cmd+Shift+U and pick MCP Logs.

```
Customize  >  xspeedhub  (on)
```

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

### 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. Cursor decides how to treat an MCP tool call by its Run Mode, and you can expand a call to see its arguments. MCP follows the same Run Modes as terminal commands, set under Settings > Agents > Approvals & Execution. The recommended default, Auto-review, runs allowlisted calls at once and sends the rest to a classifier, not to you. Allowlist runs only what you listed, and with an empty list it asks you every time. Run Everything runs every tool call without asking. xSpeed Hub has no confirmation step of its own, so a tool you allowlist, or any call under Run Everything, writes as soon as your connection allows writes. Auto-review is a model, and Cursor says it is not a security boundary.

## Prompts

- Using xSpeed Hub, what is the latest mobile LCP for shop, and how does it compare with the run before it?
- I just deployed the font change to blog. Use xSpeed Hub to run a mobile test and tell me which metric moved.
- Ask xSpeed Hub for the benchmark history on shop and show it next to my last two settings changes.

## Example session

```
You: I swapped the hero image loading on shop. Using xSpeed Hub, did mobile LCP get better?
  → get_score_history(site: shop) [read-only]: latest mobile 59, LCP 4.1 s, 12 days ago; desktop 80
Agent: The stored run predates your change, so it cannot answer that yet. I can start a fresh mobile test of the live site. It takes up to two minutes. Start it?
You: Yes.
  → run_speed_test(site: shop, strategy: mobile) [uses quota]: mobile score 62, LCP 3.5 s, CLS 0.03, saved to the Hub report history
Agent: Mobile LCP went from 4.1 s to 3.5 s on this run. One run is a single reading, so check again after a few more.
```

## How it works

1. **Read before you test**: get_score_history returns the stored PageSpeed Insights and GTmetrix runs for a site: the score per run, with LCP, FCP, CLS, TBT, Speed Index and TTFB, mobile and desktop. It starts nothing. The Hub tells the agent to use it whenever you ask what your score is, or whether it improved, because a new test spends a shared allowance.
2. **Run a new test when you need one**: run_speed_test runs a real PageSpeed Insights audit on the site from the Hub and returns the score, the Core Web Vitals and the top opportunities. strategy is mobile (the default) or desktop, and one call tests one of them. It can take up to about 2 minutes, so the agent should say it is running before it calls.
3. **Test the other device**: Mobile and desktop scores differ, often by a lot. For both, the agent makes two calls, one per strategy. A failure is reported with its reason: PageSpeed not configured, quota reached, a timeout, or a site the audit cannot reach.
4. **Measure the cache on its own**: run_benchmark times the home page with the cache bypassed and again served from cache, and returns the response times. It is a read tool, and it accepts site: "all" for every site. It does not return a Lighthouse score, so the agent must not use it to answer a PageSpeed question.
5. **Compare over time**: get_benchmark_history returns past benchmark runs, uncached against cached, together with the settings changes on the same timeline, which is how you answer "did that change help?". For PageSpeed scores over time, use get_score_history.

## Reference

| | |
| --- | --- |
| Read stored scores | get_score_history (read): PageSpeed Insights and GTmetrix runs, starts nothing |
| Metrics per run | Score, LCP, FCP, CLS, TBT, Speed Index, TTFB, for mobile and desktop |
| Run a new test | run_speed_test (write, uses the shared allowance): one PageSpeed Insights run per call |
| strategy | mobile (default) or desktop |
| Duration | Up to about 2 minutes per run |
| Why a test is a write | It spends a shared PageSpeed allowance and stores a report; it changes nothing on the site |
| Read-only access | A connection token with Read-only everywhere on, or a Viewer member's sign-in: run_speed_test is refused; get_score_history, run_benchmark and get_benchmark_history still work. An OAuth sign-in gets the scopes the client asks for |
| Benchmark | run_benchmark (read): cached against uncached response time for the home page, no Lighthouse score |
| Benchmark history | get_benchmark_history (read): past runs plus settings changes on the same timeline |
| Scheduling | The Hub does not schedule PageSpeed tests itself; its daily pass only reads reports the plugin already stored |
| Where a new test is stored | In the Hub's own report history, the one the Hub dashboard shows |

## Rules

- Check the history first. Ask for stored scores before starting a test, and run a new one only when you want a fresh measurement or something changed.
- Never answer a PageSpeed or Lighthouse question with run_benchmark. It times your own cache and carries no score.
- run_speed_test changes nothing on your site, but the Hub classes it a write because it spends a shared allowance. A connection token with Read-only everywhere on, or a Viewer sign-in, refuses it. An OAuth sign-in gets the scopes the client asks for, so there your client's approval prompt is the gate.
- Lab scores move a few points between runs of the same page. The agent should compare like with like, same site, same strategy, and not report one run's difference as a trend.
- A new test does not run on a timer. If you want a regular test, the agent has to be started by something else, such as a scheduled job in your client, and a scheduled run that spends the allowance should be one you are comfortable leaving unattended.

## Good to know with Cursor

Under Run Everything, Cursor runs every MCP tool without asking, run_speed_test included, and Auto-review hands calls that are not allowlisted to a classifier that Cursor says is not a security boundary. A chat that says "check the score after each change" can then start a test after every edit, and each test spends the shared speed-test allowance. Switch Run Mode to Allowlist (Settings > Agents > Approvals & Execution), list the read tools, and leave run_speed_test off so it asks; under the default Auto-review, unlisted calls go to a classifier. Cursor says Cloud Agents never ask for approval, so give a Cloud Agent the connection token with Read-only everywhere on.

## More prompts for this job

They work in any client connected to xSpeed Hub.

- Using xSpeed Hub, what is the mobile PageSpeed score for shop? Check the stored history before you run anything.
- Use xSpeed Hub to run a new mobile PageSpeed test on blog and tell me the score, LCP and the top opportunities.
- With xSpeed Hub, test shop on desktop and mobile and tell me which one is worse.
- Using xSpeed Hub, has the PageSpeed score on docs improved over the last few runs?
- Use xSpeed Hub to benchmark the cache on every site and tell me which one saves the least time.
- Did turning on minification on shop help? Use xSpeed Hub to compare the benchmark history around that change.
- My PageSpeed test failed on staging. Use xSpeed Hub to tell me why.

## Frequently asked questions

### Does Cursor test the code in my editor or the live site?

The live site. The Hub runs PageSpeed Insights against the address you connected, so an edit that has not been deployed will not change the result. Deploy first, then ask Cursor for the test.

### Will Cursor prompt me before it runs a speed test?

Not by default. Since Cursor 3.6 the recommended Run Mode is Auto-review, which sends calls that are not allowlisted to a classifier instead of to you. Under Allowlist, Cursor asks about any tool not on the list, and under Run Everything it asks nothing. The Hub has no confirmation step of its own, and run_speed_test runs as soon as your connection allows writes, so Allowlist mode and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) are the checks you have.

### What is the difference between run_speed_test and run_benchmark?

run_speed_test runs a real PageSpeed Insights audit and returns a Lighthouse score with Core Web Vitals. run_benchmark measures how fast your own cache answers compared with an uncached request for the home page, and returns no Lighthouse score. Use the first for "what is my PageSpeed score" and the second for "is my caching working".

### How long does a PageSpeed test take?

A single run can take up to about 2 minutes, so the agent should tell you it has started before it calls. One call tests one device, mobile or desktop, so checking both takes two calls.

### Can I ask for the last score without running a new test?

Yes. get_score_history reads the stored PageSpeed Insights and GTmetrix runs for the site and starts nothing. The Hub tells the agent to read it first whenever you ask what your score is, because a new test spends a shared allowance.

### Will the Hub run PageSpeed tests on a schedule?

No. The Hub does not schedule PageSpeed tests itself. Its daily pass re-verifies sites, snapshots cache status and pulls the PageSpeed and GTmetrix reports the plugin has already stored, and it can alert on a score regression. If you want regular new tests, they have to be started by a client that can run scheduled jobs.

### Why is a speed test treated as a write tool?

It does not change your site. The Hub classes run_speed_test as a write because it spends a shared PageSpeed allowance and stores a report, and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) should not be able to cost the owner anything. Such a connection can still read stored scores with get_score_history.

## Track PageSpeed scores with other agents

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

## More with Cursor

- [Purge the WordPress cache with Cursor](https://xspeedcache.com/agent/cursor/purge-cache/)
- [Find out why WordPress pages are not cached with Cursor](https://xspeedcache.com/agent/cursor/troubleshoot-cache/)
- [Scan a website for speed problems with Cursor](https://xspeedcache.com/agent/cursor/speed-scan/)
- [Raise a WordPress site's PageSpeed score with Cursor](https://xspeedcache.com/agent/cursor/optimize-site/)
- [Tune WordPress cache settings with Cursor](https://xspeedcache.com/agent/cursor/cache-settings/)
- [Warm the WordPress cache with Cursor](https://xspeedcache.com/agent/cursor/preload-cache/)
- [Set up the Redis object cache with Cursor](https://xspeedcache.com/agent/cursor/object-cache/)
- [Manage Cloudflare caching with Cursor](https://xspeedcache.com/agent/cursor/cloudflare/)
- [Manage every WordPress site at once with Cursor](https://xspeedcache.com/agent/cursor/fleet/)

## Documentation

- How to run a speed test: https://xspeedcache.com/docs/external-score/
- PageSpeed Insights integration: https://xspeedcache.com/docs/pagespeed-insights-integration/
- Running speed tests in xSpeed Hub: https://xspeedcache.com/docs/hub-speed-tests-and-notifications/
- How to run a PageSpeed audit: https://xspeedcache.com/docs/pagespeed/