How Zed handles this
Zed is where you edit the template, and the agent panel sits next to it. You ask how the site scores, and the agent calls get_score_history and returns the stored runs: score, LCP, FCP, CLS, TBT, Speed Index and TTFB, for mobile and desktop. It works well for a quick comparison, such as the last two mobile runs side by side, with a sentence on which metric explains the gap.
To measure again, the agent calls run_speed_test, a PageSpeed Insights run from the Hub, mobile or desktop, taking up to about two minutes. For a fast timing of the home page cached and uncached it can use run_benchmark, which has no Lighthouse score, so the two should not be mixed in one comparison. get_benchmark_history lines past benchmark runs up with your settings changes, which helps when you are asking whether a change was the cause.
Zed's default tool permission is confirm, so it prompts for every call, reads included. In practice a trend review means several approvals in a row: list_sites, get_score_history, perhaps get_benchmark_history. That is slower than other clients, and it also means that no tool call, including a test, runs while you are looking away. When a test does run, it tests one device per call and saves the result to the Hub's own report history, the Reports tab of the dashboard. get_score_history reads the plugin's stored runs, so do not expect the new result there.
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.
{
"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.
Settings → AI → MCP Servers
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.
With xSpeed Hub, compare the last two mobile runs on shop and say which metric changed most.
Use xSpeed Hub to run a desktop test on blog now and show the score next to the previous desktop run.
Ask xSpeed Hub for the benchmark history on shop and match it against my recent settings changes.
What happens, step by step
PageSpeed Insights is Google's Lighthouse audit, and its score and Core Web Vitals are the numbers most people mean by "my speed". Through xSpeed Hub an agent can read the scores a site has already stored, run a new PageSpeed test on mobile or desktop, and read or run a separate benchmark of cached against uncached response time. The three answer different questions, and the Hub tells the agent which to use for each.
01
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.
02
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.
03
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.
04
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.
05
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 worth keeping
- 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 Zed
With confirm as the default, a review that reads three or four things asks you three or four times, and the habit is to loosen the setting. Zed documents per-tool entries for MCP tools and no wildcard, so allow each read tool by name, or use the Always for tool button in the prompt, and keep run_speed_test on confirm. Setting the global default to allow auto-approves every tool, writes included. Reads change nothing on your sites, but each speed test spends the shared allowance, and the Hub has no confirmation of its own to catch a test you did not mean to start.
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
Keep going
Track PageSpeed scores with other agents
More with Zed
Documentation
- How to run a speed test
- PageSpeed Insights integration
- Running speed tests in xSpeed Hub
- How to run a PageSpeed audit
- How to write prompts for xSpeed Hub
- Zed + xSpeed
- Every AI agent that works with xSpeed
From the blog
- Reading a PageSpeed Report in 2026: 30% of the Score Is a Metric Google Does Not Rank You On
- 45% of the WordPress Sites Our Scan Calls Clean Are Failing Google in 2026: Lab Scores Against Field Data
- The Same Page Scored 61 and 73 Twelve Minutes Apart: How to Benchmark WordPress Caching Plugins in 2026