# Scan a website for speed problems with Grok

> Scanning a site's speed with Grok means asking xAI's chat assistant on grok.com to run an xSpeed Scan through a custom connector, and getting the graded report and its link back in the conversation.

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

You are in a Grok conversation about something else, a redesign or a marketing plan, and the question of speed comes up. Rather than leave the chat, you ask Grok to scan the site. With the no-account xSpeed Scan MCP added as a custom connector on grok.com, Grok calls run_speed_scan on the public URL and waits for the result, which takes 20 to 60 seconds. It answers with a grade out of 100, the desktop run as the headline and the mobile run beside it, the failing checks with their evidence, and a report link anyone can open.

xAI requires only that a custom connector's server be reachable over the public internet, and the Scan MCP needs no sign-in, so it is the lightest connector you can add. It is also read-only in every tool, which matters in Grok more than in most clients. xAI's connector documentation describes no per-tool approval setting and says Grok can use a connector's tools whenever your question relates to that service, so a connector that cannot change anything is the comfortable one to leave switched on.

For your own sites, add xSpeed Hub as a second custom connector and sign in. Then run_speed_scan takes a site handle, and get_speed_scan reads a site's scan history, so you can ask what shop scored last month without starting a measurement. The Hub classes run_speed_scan as a write tool, because every scan spends a shared speed-test allowance even though it changes nothing on the site. When you re-test after a change, say "fresh", because the same URL within ten minutes returns the existing report.

## Set up Grok 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 as a custom connector

Go to grok.com/connectors, click New Connector and select Custom. Enter this as the MCP server URL and complete the authentication: approve access on the xSpeed Hub page that opens. Grok then reads the Hub's tools and makes them available in your conversations.

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

### 3. Ask a first question

Start a chat and ask something that names xSpeed Hub, so Grok reaches for the connector. A list of your sites with their cache status means the connection works.

```
Use xSpeed Hub to list my sites and tell me which ones have page caching turned off.
```

### 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 Grok 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/grok/

### 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. xAI's connector documentation describes no per-tool approval setting. It says Grok can use a connector's tools whenever your questions relate to that service. xSpeed Hub has no confirmation step of its own, so a purge or a settings change runs as soon as Grok calls it and your connection allows writes. The Hub tells the agent to confirm the target site and to ask once before a write that touches every site, but that is an instruction, not a lock. If you want Grok to read and never change anything, sign in as a Viewer member of the workspace, which only ever gets read access. Otherwise read what Grok says it is about to do before you answer yes.

## Prompts

- Use the xSpeed Scan MCP to scan [site URL] and tell me the desktop and mobile grades and the biggest fix.
- Using xSpeed Hub, what did shop score on its last scan? Do not start a new one.
- With the xSpeed Scan MCP, run a fresh mobile-only scan of the same URL and tell me whether the grade changed.

## Example session

```
You: Use the xSpeed Scan MCP to check how fast example-florist.com is before we plan the redesign.
  → run_speed_scan(url: example-florist.com, strategy: both) [read-only]: Desktop grade C, mobile grade D. Ranked fixes: page cache (slow first byte), image size, render-blocking font stylesheet. Report link included.
Agent: Desktop C and mobile D. The server builds every page for each visitor, which is the top fix, then heavy images and a font stylesheet that blocks rendering. The redesign can fix the last two; the first is hosting and caching.
You: Is mobile worse only because of images?
Agent: Images are the biggest mobile item, but the slow first byte hurts both runs. The report ranks them by the points each fix would recover.
```

## 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 Grok

With no approval setting described for connectors, a Hub scan runs as soon as Grok decides your question calls for one, and each one spends the allowance. xSpeed Hub has no confirmation step of its own. If you want Grok to read scan history and never start a Hub scan, sign in to the Hub connector as a Viewer member of the workspace, which refuses run_speed_scan and still allows get_speed_scan; the connection token's Read-only everywhere switch is not part of this setup, because the connector signs in with OAuth. On the Scan MCP the limit is four scans per caller per ten minutes. Reports started through the Scan MCP are public in the scan directory by default, so a scan of a prospect's site leaves a report anyone with the link can open. On Grok Business and Enterprise, a team admin provisions each connector in the cloud console before members can use 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.

- 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 Grok scan a website with no account?

Yes. Add the xSpeed Scan MCP as a custom connector on grok.com. It needs no sign-in, grades any public URL and cannot change anything. The limit is four scans per caller per ten minutes.

### Will Grok start a scan on my own site without asking?

It can. xAI describes no per-tool approval setting for connectors, and the Hub has no confirmation step of its own, so run_speed_scan runs when Grok calls it and spends the shared allowance. A Viewer sign-in refuses it and still lets Grok read your scan history.

### 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 Code](https://xspeedcache.com/agent/claude-code/speed-scan/) · [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 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 Grok

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