Scan a website for speed problems with Claude

Scanning a site's speed with Claude means typing a URL into the chat and getting back an xSpeed Scan, a graded speed report with the fixes ranked and a link you can forward.

list_sitesget_speed_scanrun_speed_scan

Last updated: October 2026

Example session · Claude

You: A prospect says their site is slow. Use the xSpeed Scan MCP to check how example-bakery.com looks.

run_speed_scan(url: example-bakery.com, strategy: both) read-only scan mcp
→ Report ready. Desktop grade C, mobile grade D. Top failing check: slow first byte, pages are rendered on every request with no cache in front. Next on mobile: heavy images.

Claude: The server builds the page for every visitor, which is why the first byte is slow. Mobile is weaker because of heavy images. The report also shows real-visitor numbers when Chrome has enough traffic for the site. Here is the link you can send them.

You: Good. Which fix first?

Claude: A page cache. It is the top item in the ranked list and it also helps the mobile run.

How Claude handles this

You are on a call, or reading an email, and someone says their site feels slow. You do not want to open three tools. In a Claude chat you type the address and ask how fast it is. If you added the no-account xSpeed Scan MCP as a custom connector, Claude calls run_speed_scan on that URL and answers in the same thread. There is nothing to install on the other person's site and nothing for them to approve, because the scan runs from the xSpeed servers against the public page.

What comes back is a grade out of 100 with a letter, the desktop run as the headline and the mobile run beside it. Claude reads the failing checks, each with its evidence, and explains them in plain words. It also gives you the report link, which anyone can open. One detail worth asking about: the grade is lab data from one Lighthouse run, while Google looks at real Chrome visitors over 28 days. The report shows both, so ask Claude whether the real-visitor numbers pass before you say the site passes Core Web Vitals.

If the site is one of yours and sits in xSpeed Hub, the same chat can use the Hub connector instead. Then run_speed_scan takes a site handle, and get_speed_scan reads the scan history so you can see what a site scored last month without starting anything.

Set up Claude once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Claude 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 custom connector

Go to Customize > Connectors and click Add custom connector. Name it xspeedhub and paste the URL. Under Authentication choose Sign in now, and if Claude asks how it identifies itself, choose Register automatically, which uses dynamic client registration. Click Add. On a Team or Enterprise plan an Owner does this under Organization settings > Connectors, with Add, then Custom, then Web.

Text

https://app.xspeedcache.com/xspeed/mcp

3Connect and turn it on in a chat

Click Connect on the xspeedhub connector and approve access on the xSpeed Hub page that opens. Then, in a conversation, click + in the message box, choose Connectors and switch xspeedhub on. Claude can use the connector only in conversations where that toggle is on.

Text

+  >  Connectors  >  xspeedhub (on)

4Add the xSpeed Scan MCP for sites you do not run

Prompts that scan a public URL use the xSpeed Scan MCP, a separate server from the Hub. Add it to Claude the same way as the Hub above, as a second server (xspeedscan, for example) with the URL https://xspeedcache.com/scan/mcp, and leave out any sign-in setting, such as an OAuth or auth option or an Authorization header, because the Scan MCP needs no account, token or sign-in. On a plan that allows one custom connector, add whichever server the prompts you use need.

Text

https://xspeedcache.com/scan/mcp

1 / 4

Full Claude 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. Claude can ask for your approval before it uses a connector tool. Allow once runs that call, and Always allow skips the prompt for that tool from then on. Under Customize > Connectors you can set each tool, or a group of tools, to Always allow, Needs approval or Blocked. xSpeed Hub has no confirmation step of its own, so a write tool you set to Always allow runs as soon as your connection allows writes. Keep purge_cache, update_settings, toggle_cache and the other write tools on Needs approval, block the ones you never want. For read-only access, sign in as a Viewer member of the workspace, or use the connection token with Read-only everywhere on, which needs the Request headers beta. The switch does not apply to a normal OAuth sign-in.

What do I ask?

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

Prompt for Claude

How fast is [your site URL]? Use the xSpeed Scan MCP to scan it and explain the three biggest problems like I am not technical.

Prompt for Claude

With the xSpeed Scan MCP, scan the same site again on mobile only and tell me whether the grade changed.

Prompt for Claude

From that xSpeed Scan MCP report, give me one paragraph I can paste into an email to the site owner, with the report link.

What happens, step by step

An xSpeed Scan grades a site from 0 to 100 using server probes (time to first byte, compression, cache evidence, redirects, platform detection) plus a Lighthouse run, and names the fix for every failing check. An agent can start one two ways. Through xSpeed Hub, run_speed_scan scans a site you have connected. Through the no-account Scan MCP at https://xspeedcache.com/scan/mcp, it scans any public URL and cannot change anything. Either way you get a report link to share.

Check what the site already scored

get_speed_scan without a scan id returns the site's scan history, newest first, plus a summary of the latest report. It starts nothing and spends nothing, so the Hub tells the agent to read it first when you ask what a site scored.

Start a scan

run_speed_scan runs the full scan on a site you connected to the Hub. strategy is both (the default), desktop or mobile; one device alone costs half the engine's quota. The scan takes 20 to 60 seconds. The Hub waits about 50 seconds and, if the scan is still running, hands back a scan id.

Poll if it is still running

Call get_speed_scan with scan_id. While the scan runs it returns the running status and a note to ask again in about 20 seconds. The report page is live from the start and refreshes itself.

Read the result

The summary carries the grade, the four dimension scores, what was measured and the top fixes ranked by points recoverable, each with the xSpeed feature that fixes it. The headline grade is the desktop run. The mobile run is graded alongside it, so the agent should mention both when they differ.

Scan a site you do not run

For any other public URL, the agent uses the Scan MCP at https://xspeedcache.com/scan/mcp. There is no account and no sign-in. It takes a url, returns the same graded report and a link at xspeedcache.com/scan/r/<id>, and is limited to 4 scans per caller per 10 minutes.

Fix, wait, re-scan

After a change, wait several minutes and scan again with fresh: true. Without it, the scan service reuses any report from the last 10 minutes and the agent will show you the old number.

Reference

Hub route	run_speed_scan, then get_speed_scan with scan_id; only for sites connected to your Hub
Scan MCP route	https://xspeedcache.com/scan/mcp, no account, 5 tools, read-only, any public URL
Scan MCP limit	4 scans per caller per 10 minutes
Why run_speed_scan is a write	It spends a shared scan allowance and stores a report; it changes nothing on the site
Read-only Hub connection	run_speed_scan is refused; get_speed_scan still works. Applies to the connection token with Read-only everywhere on and to a Viewer sign-in; an OAuth sign-in gets the scopes the client asks for
Duration	20 to 60 seconds; the Hub waits about 50 seconds, then returns a scan id
Poll argument	scan_id on the Hub tool, scanId on the Scan MCP tool
strategy	both (default), desktop or mobile; one device costs half the quota and becomes the headline
fresh	true forces a new measurement; otherwise a report from the last 10 minutes is reused
Report link	xspeedcache.com/scan/r/<id>; add .md for a Markdown twin an agent can read
Report visibility	Hub scans are filed unlisted; Scan MCP scans are public in the scan directory by default

Rules worth keeping

Read before you spend. Ask for the scan history first; start a new scan only when you want a fresh measurement or something changed.
A report link is not private. An unlisted report is kept out of the scan directory and search, but anyone with the URL can open it. A scan started through the Scan MCP is public by default.
run_speed_scan changes nothing on your site, but the Hub classes it a write, so a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) refuses it and your client may prompt for it. Use get_speed_scan, or the Scan MCP for a public URL, when you want a strictly read-only route.
Compare like with like. A scan that lost its Lighthouse run is marked partial and is not comparable with a full one, and the lab grade is not the same as real-visitor Core Web Vitals, which the report shows separately.
A scan cannot reach private, local or password-protected sites, and a site behind a bot challenge returns a report that says its server checks were not measured.

Good to know with Claude

The Free plan allows one custom connector, so pick the Scan MCP or the Hub for that slot, or move to a paid plan. On Team and Enterprise plans an Owner adds the connector for the organization and each member connects with their own account. Switch it on for each chat from + > Connectors, or Claude will not call it. Claude can ask before using a connector tool, and under Customize > Connectors each tool is Always allow, Needs approval or Blocked. Choosing Always allow on the Hub's run_speed_scan means later scans run without asking, and each one spends the shared speed-test allowance. Anthropic notes that Research can call connector tools without further approval, so set run_speed_scan to Blocked before you use Research with the Hub connector. The Scan MCP is read-only, so Always allow there costs nothing but your four scans per ten minutes. A scan through it is listed in the public scan directory by default, and a scan through the Hub is filed unlisted, though its link still opens for anyone who has it.

More prompts for this job

Prompts about your own sites work in any client connected to xSpeed Hub. A prompt that scans a site you do not run, or names the scan server, needs the xSpeed Scan MCP from the setup above.

Prompt

Using xSpeed Hub, what did the shop site score on its last speed scan? Do not start a new one.

Prompt

Use xSpeed Hub to run a speed scan on blog and give me the three fixes that recover the most points, plus the report link.

Prompt

With xSpeed Hub, scan only the mobile view of shop and tell me the grade.

Prompt

I changed the theme this morning. Use xSpeed Hub to run a fresh scan on docs and compare it with the previous report.

Prompt

Use the xSpeed Scan MCP to grade [competitor URL] and tell me what its biggest weaknesses are.

Prompt

The speed scan on shop is still running. Ask xSpeed Hub to check it again and tell me when it finishes.

Frequently asked questions

Not for a public site. The xSpeed Scan MCP needs no account and no key, and Claude can use it on any URL that is reachable from the internet. An account and xSpeed Hub are only needed to scan your own sites by handle or to read their scan history.

Yes. Every scan has a shareable report link on xspeedcache.com. Ask Claude for the link along with the summary, and the other person can open the full report without using Claude at all.

run_speed_scan runs the full xSpeed Scan: server probes plus Lighthouse, a 0 to 100 grade across four dimensions, the fix for every failing check and a shareable report link. run_speed_test returns a raw PageSpeed Insights score with Core Web Vitals and no graded report.

Yes, through the xSpeed Scan MCP at https://xspeedcache.com/scan/mcp. It needs no account and no sign-in, accepts any public URL and is read-only. The Hub route only scans sites you connected to your own workspace.

The Scan MCP allows 4 scans per caller per 10 minutes. Scanning the same URL again within 10 minutes returns the existing report unless the agent passes fresh: true. A Hub scan spends a shared allowance of the scan service, which is why the Hub treats it as a write tool.

Reports started from the Hub are filed as unlisted, which keeps them out of the public scan directory and search results, but the link itself still opens for anyone who has it. Reports started through the Scan MCP are public by default.

The headline grade is the desktop run, because it is the one you can reproduce in your own browser. The mobile run is graded on the same rubric and returned alongside it. Google ranks on mobile, so when the two differ the agent should tell you both.

Keep going

Scan a site's speed with other agents

More with Claude

Purge the cache Find out why pages are not cached Track PageSpeed scores Raise the PageSpeed score Tune cache settings Warm the cache Set up Redis object cache Manage Cloudflare Manage every site at once

Documentation

From the blog

Scan a site's speed, from Claude.

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

Open xSpeed Hub Claude setup