# Scan a website for speed problems with Claude Code

> Scanning a site's speed with Claude Code means asking it, in the terminal where you ship changes, to run an xSpeed Scan through xSpeed Hub and hand back the graded report with its shareable link.

Page: https://xspeedcache.com/agent/claude-code/speed-scan/
Last updated: October 2026

The moment is right after a change lands. You merged a caching tweak or swapped a plugin from this terminal, and you want to know whether the site is faster, with a grade you can point at instead of a feeling. You tell Claude Code which site. It calls list_sites to match the handle, then run_speed_scan through the xspeedhub server you added. If you only want to know what the site already scored, ask for the history first: get_speed_scan with no scan id reads past reports and spends nothing.

A scan combines server probes (time to first byte, compression, cache evidence, the redirect chain) with a Lighthouse run, and grades the result out of 100 across four dimensions. The headline grade is the desktop run, and the mobile run is graded alongside it on the same rubric. Claude Code gets back the failing checks ranked by points you could recover, the xSpeed feature behind each fix, and a report link on xspeedcache.com that you can open or share. It waits about 50 seconds. If the scan is still running, it receives a scan id and polls get_speed_scan. Ask for a fresh run when you are re-testing after a change, because the same request within ten minutes returns the existing report.

For a site you do not run, such as a competitor or a prospect, add the no-account Scan MCP as a second server. It is the same engine on any public URL, read-only, with four scans per caller per ten minutes. Those calls show up under a separate server name in the session, so you can always tell which route Claude Code used.

## Set up Claude Code 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 Claude Code

Run this once. --scope user makes the server available in every project; leave it off and it applies to the current project only, which is Claude Code's default.

```bash
claude mcp add --transport http --scope user xspeedhub https://app.xspeedcache.com/xspeed/mcp
```

### 3. Sign in with /mcp

Start Claude Code, run /mcp, pick xspeedhub and finish the sign-in in your browser. You approve access on an xSpeed Hub page; there is no token to paste, and Claude Code keeps the credentials it receives and refreshes them.

```
/mcp
```

### 4. Add 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 Code 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.

```
https://xspeedcache.com/scan/mcp
```

Full setup: https://xspeedcache.com/agent/claude-code/

### 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 Code asks before it runs an MCP tool unless a permission rule already allows it, or you work in auto mode, where a classifier reviews actions instead of you, or in bypassPermissions mode, which skips prompts. A rule such as mcp__xspeedhub__get_cache_status allows one tool, and mcp__xspeedhub__get_* allows every read whose name starts with get_. Keep purge_cache, update_settings, toggle_cache and the other write tools on the prompt, because the Hub itself runs a write as soon as your connection allows it.

## Prompts

- Use xSpeed Hub to scan shop, tell me the desktop and mobile grades, and list the three failing checks that would recover the most points.
- Using xSpeed Hub, what did the blog site score last time? Read the scan history only, do not start a new scan.
- I just deployed the cache changes to shop. With xSpeed Hub, run a fresh scan and compare it with the previous report.

## Example session

```
You: I merged the cache changes an hour ago. Use xSpeed Hub to scan shop again and tell me if it got faster.
  → get_speed_scan(site: shop) [read-only]: Latest report is from yesterday: desktop grade C, mobile grade D. Top failing check: time to first byte
  → run_speed_scan(site: shop, fresh: true, strategy: both) [uses quota]: Done in about 40 s. Desktop grade B, mobile grade C. Top failing check: image weight; time to first byte passes. Report link included.
Agent: Both runs moved up a grade since yesterday. Time to first byte is no longer the top failing check; image weight is. Mobile is still the weaker run, and Google ranks on mobile, so I would fix that next. Here is the report link to share.
```

## How it works

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

- 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 Code

Claude Code prompts per MCP tool unless a permission rule allows it, or auto mode (a classifier reviews actions instead of you) or bypassPermissions mode (no prompts) is on. The Hub classes run_speed_scan as a write tool because every scan spends the shared speed-test allowance, even though it changes nothing on your site. A rule such as mcp__xspeedhub__get_speed_scan allows the history read and leaves run_speed_scan on the prompt, while a rule that allows the whole xspeedhub server lets a looping session spend the allowance without one. Allow get_speed_scan on its own and leave run_speed_scan to ask. A read-only Hub connection refuses run_speed_scan outright, which is the setting to use for a session you do not watch. For Claude Code that means the connection token, sent as a header, with Read-only everywhere on, or a Viewer sign-in.

## 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.

- Using xSpeed Hub, what did the shop site score on its last speed scan? Do not start a new one.
- 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.
- With xSpeed Hub, scan only the mobile view of shop and tell me the grade.
- I changed the theme this morning. Use xSpeed Hub to run a fresh scan on docs and compare it with the previous report.
- Use the xSpeed Scan MCP to grade [competitor URL] and tell me what its biggest weaknesses are.
- The speed scan on shop is still running. Ask xSpeed Hub to check it again and tell me when it finishes.

## Frequently asked questions

### Can Claude Code scan a site that is not in my xSpeed Hub?

Not through the Hub, which only scans sites in your workspace. Add the xSpeed Scan MCP as a second server and Claude Code can grade any public URL with no account. That route is read-only and limited to four scans per caller per ten minutes.

### Does a scan change my WordPress site?

No. A scan only measures. The Hub still classes run_speed_scan as a write tool because it spends the shared speed-test allowance, so your Claude Code permission rule and your connection scope decide whether it runs without a prompt.

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

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.

### Can an agent scan a site that is not in my Hub?

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.

### How many scans can I run?

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.

### Is my scan report public?

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.

### Which score does the scan headline show, desktop or mobile?

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.

## Scan a site's speed with other agents

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

## More with Claude Code

- [Purge the WordPress cache with Claude Code](https://xspeedcache.com/agent/claude-code/purge-cache/)
- [Find out why WordPress pages are not cached with Claude Code](https://xspeedcache.com/agent/claude-code/troubleshoot-cache/)
- [Run and track PageSpeed tests with Claude Code](https://xspeedcache.com/agent/claude-code/pagespeed-tests/)
- [Raise a WordPress site's PageSpeed score with Claude Code](https://xspeedcache.com/agent/claude-code/optimize-site/)
- [Tune WordPress cache settings with Claude Code](https://xspeedcache.com/agent/claude-code/cache-settings/)
- [Warm the WordPress cache with Claude Code](https://xspeedcache.com/agent/claude-code/preload-cache/)
- [Set up the Redis object cache with Claude Code](https://xspeedcache.com/agent/claude-code/object-cache/)
- [Manage Cloudflare caching with Claude Code](https://xspeedcache.com/agent/claude-code/cloudflare/)
- [Manage every WordPress site at once with Claude Code](https://xspeedcache.com/agent/claude-code/fleet/)

## Documentation

- xSpeed Scan: free website speed test: https://xspeedcache.com/docs/speed-scan/
- xSpeed Scan MCP: speed-test any site from your AI assistant: https://xspeedcache.com/docs/scan-mcp/
- How to run a full site scan: https://xspeedcache.com/docs/scan/
- Running speed tests in xSpeed Hub: https://xspeedcache.com/docs/hub-speed-tests-and-notifications/