# Run and track PageSpeed tests with OpenClaw

> Tracking PageSpeed scores with OpenClaw means letting its always-on agent read your stored PageSpeed history on a schedule you set and report drops, using xSpeed Hub as the data source.

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

OpenClaw runs all the time and has automations, which suits a job nobody remembers to do. Set one up for Monday morning: read get_score_history for every site you care about, compare each latest run with the one before, and send a short report listing any site whose mobile or desktop score fell. The Hub itself has no scheduler for agent prompts, so the timer is OpenClaw's, and the Hub only answers when OpenClaw calls it.

Keep the scheduled job report-only. get_score_history reads what is stored and starts nothing, and run_benchmark can time every site cached and uncached in one call with no Lighthouse score. Neither changes a site. What the schedule will not do is produce new Lighthouse data on its own, because the Hub does not run scheduled PageSpeed tests. The Hub does pull the plugin's stored PageSpeed and GTmetrix reports each day and sends its own alerts for score regressions, so your weekly report and those alerts complement each other.

When the report shows a drop, you can switch to a normal conversation: ask OpenClaw to run run_speed_test on that one site and compare it with the stored run. That test takes up to about two minutes. Treat it as a deliberate step with you present, since each run spends the shared speed-test allowance. Its result goes to the Hub's own report history, so next week's get_score_history report may not list it.

## Set up OpenClaw 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. Save xSpeed Hub as an MCP server

Run this on the machine that hosts your OpenClaw Gateway. Set the transport to streamable-http: OpenClaw falls back to SSE when you leave it out. With --auth oauth the command saves the server without a connection test, because sign-in has to happen first.

```bash
openclaw mcp add xspeedhub \
  --url https://app.xspeedcache.com/xspeed/mcp \
  --transport streamable-http \
  --auth oauth
```

### 3. Sign in with openclaw mcp login

OpenClaw prints an authorization URL and listens on a loopback address for the callback. Open the URL, sign in to xSpeed Hub and approve; the token exchange finishes by itself. There is no token to paste. If your browser is on another machine, copy the code from the redirect and pass it back with openclaw mcp login xspeedhub --code. Then check the connection.

```bash
openclaw mcp login xspeedhub
openclaw mcp doctor xspeedhub --probe
```

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

### 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. OpenClaw gives you two client-side gates, and the Hub adds none. First, openclaw mcp tools xspeedhub --include limits which tools exist for the agent, so a list of read tools keeps every write out of reach. Second, when the Codex runtime runs your agent turns, MCP tool approvals follow the session's permission posture, and the default full-permission posture does not prompt. openclaw mcp configure xspeedhub --approval prompt asks on every call, and Allow Always saves a grant for that one tool with any arguments. OpenClaw's docs describe that per-call prompt for the Codex runtime; with its own embedded runtime, use the tool filter to decide what the agent can call. The Hub has no confirmation step of its own.

## Prompts

- Every Monday morning, use xSpeed Hub to read the PageSpeed history for all my sites and report any whose mobile or desktop score dropped since the previous run. Do not run any tests.
- Ask xSpeed Hub for the latest scores on shop and blog now and tell me which one is further behind on mobile.
- This morning's report flagged docs. With xSpeed Hub, run one mobile test on docs and compare it with the stored run.

## Example session

```
You: Use xSpeed Hub to run the Monday PageSpeed report: history only, no new tests.
  → list_sites [read-only]: 4 sites in the default workspace
  → get_score_history(site: shop) [read-only]: latest mobile 55, previous 61; desktop 82, previous 82
  → get_score_history(site: docs) [read-only]: latest mobile 71, previous 70; desktop 90, previous 89
  → get_score_history(site: blog) [read-only]: no run newer than last week; latest mobile 66
  → get_score_history(site: storefront) [read-only]: no run newer than last week; latest mobile 62
Agent: Report: shop mobile fell six points to 55, desktop flat. Docs rose by one on both devices. Blog and storefront had no new run this week. No tests were started.
```

## 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 OpenClaw

Do not let the schedule run run_speed_test. An automation runs unattended in a fresh session, nobody is there to approve it, each run spends the shared speed-test allowance, and the Hub has no confirmation step to catch a loop. Limit the automation to a tool allowlist that names only list_sites and get_score_history, and connect OpenClaw read-only to the Hub, with the connection token and Read-only everywhere on or a Viewer sign-in. A read-only connection refuses every write tool, so the job can read history and benchmarks and cannot start a test even if its prompt drifts. OpenClaw prompts per call only when the Codex runtime runs your turns and the server is set to prompt, and the default posture does not prompt.

## 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 xSpeed Hub schedule PageSpeed tests for OpenClaw?

No. The Hub has no scheduler for agent prompts and does not run scheduled PageSpeed tests. It re-checks sites and pulls stored reports each day, and OpenClaw's own automation decides when to call the Hub. A scheduled read of get_score_history is the report-only way to use it.

### Can the scheduled report show a drop it never measured itself?

It can show a drop in the stored history, which is what the plugin stored on each site. A run_speed_test you started is saved in the Hub's own report history instead. If nothing new was measured that week, the report will say there is no new run rather than show an old number as fresh.

### 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/) · [Cursor](https://xspeedcache.com/agent/cursor/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/) · [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 OpenClaw

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