Scan a website for speed problems with ChatGPT dots

Scanning site speed with a ChatGPT dot means asking OpenAI's always-on agent to track xSpeed Scan grades for your sites, reading the history for free and spending a fresh scan only when the last report is old.

list_sitesget_speed_scanrun_speed_scan

Last updated: October 2026

Example session · ChatGPT dots

You: Use xSpeed Hub to check shop's speed every Monday. Scan only if the last report is over a week old.

ChatGPT dots: Scheduled for Mondays. Running the first check now.

get_speed_scan(site: shop) read-only
→ Latest report 11 days old: desktop grade B, mobile grade C. 5 scans in history.

ChatGPT dots: The last report is 11 days old, so your rule says scan. A fresh scan spends part of the shared allowance. Run it?

You: Yes, run it.

run_speed_scan(site: shop, fresh: true, strategy: both) uses quota
→ Desktop grade B, mobile grade B. Top failing check: render-blocking stylesheet. Report link included.

ChatGPT dots: Mobile moved from C to B and desktop held at B. The top failing check is now a render-blocking stylesheet. Next Monday I will read the history first again.

How ChatGPT dots handles this

A dot keeps working between conversations, so the speed job it suits is the one you forget to do: checking every week whether a site got slower. Your dot uses the xspeedhub app you created in ChatGPT developer mode, shared through plugin permissions. Ask it to keep an eye on shop's speed and it starts with get_speed_scan, which returns the site's scan history and a summary of the latest report and spends nothing. Only when that report is stale, or you changed something, does it call run_speed_scan for a fresh graded scan.

A scan grades the site out of 100 from server probes (time to first byte, compression, cache evidence, the redirect chain) and a Lighthouse run. The desktop run is the headline and the mobile run is graded beside it, so the dot should report both when they differ, since Google ranks on mobile. Each failing check comes ranked by points recoverable with the xSpeed feature that fixes it, and every scan has a report link the dot can post in the conversation. The Hub waits about 50 seconds; if the scan is still running it returns a scan id that the dot polls with get_speed_scan.

For a competitor or a prospect that is not in your Hub, the no-account xSpeed Scan MCP grades any public URL and is read-only. ChatGPT developer mode offers No Authentication for an app, so the Scan MCP can sit beside the Hub app in your plugins. In a chat, ChatGPT asks you to confirm write actions by default and treats a tool without a read-only annotation as a write. The Hub's tools carry no such annotation, and the Hub classes run_speed_scan as a write because each scan spends the shared speed-test allowance, even though it changes nothing on your site.

Set up ChatGPT dots once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the ChatGPT dots 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.

2Create the xspeedhub app in ChatGPT

In ChatGPT on the web, turn on Developer mode under Settings, Security and login. Open Plugins, select the plus button and create a developer-mode app named xspeedhub with this URL and OAuth. Click Scan Tools, approve access on the xSpeed Hub page that opens, then click Create. If ChatGPT already has the app, skip this step. On a Business workspace only an admin or owner can turn on developer mode and publish the app.

Text

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

3Check that your dot can see it

OpenAI says plugin permissions are shared across dots and ChatGPT. Open your dot's profile, then Customize and Plugins, and check that xspeedhub is there. That screen uses the shared ChatGPT settings, and OpenAI notes the apps available to a dot may differ, so confirm it before you hand over a task.

Text

Dot profile  >  Customize  >  Plugins  >  xspeedhub

4Add a custom rule for site changes

Under Customize, Custom rules, describe the action and pick a behavior: Take action without asking, Take action if pre-approved, Ask before taking action, or Hand off to you. Add a rule that covers purging a cache, changing settings or running a speed test through xSpeed Hub, and choose Ask before taking action.

Text

Customize  >  Custom rules  >  xSpeed Hub changes: Ask before taking action

5Add 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 ChatGPT dots 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 / 5

Full ChatGPT dots 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. In a ChatGPT chat, write actions from a developer-mode app need your confirmation by default, and ChatGPT treats a tool without a read-only annotation as a write. xSpeed Hub's tools carry no such annotation. A dot comes with OpenAI's defaults for which actions need approval, and Custom rules let you set, for an action you describe, Take action without asking, Take action if pre-approved, Ask before taking action or Hand off to you. xSpeed Hub has no confirmation step of its own, so a rule that lets your dot act without asking runs a purge or a settings change as soon as your connection allows writes. Keep xSpeed Hub changes on Ask before taking action. For read-only access, sign in as a Viewer member of the workspace; the connection token's Read-only everywhere switch does not apply, because the app signs in with OAuth.

What do I ask?

Three prompts written for ChatGPT dots. More for this job are below.

Prompt for ChatGPT dots

Every Monday, use xSpeed Hub to read shop's scan history and run a fresh scan only if the latest report is over a week old.

Prompt for ChatGPT dots

With xSpeed Hub, what did blog score on its last scan? Read the history and do not start a new one.

Prompt for ChatGPT dots

Use the xSpeed Scan MCP to grade [competitor URL] and post the desktop and mobile grades 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 ChatGPT dots

A scheduled task that calls run_speed_scan every time it fires spends the allowance unattended, and xSpeed Hub has no confirmation step of its own to stop it. Word the scheduled prompt so it reads the history first and scans only when the latest report is older than a week, and keep a Custom rule on Ask before taking action for xSpeed Hub actions that spend or change anything. A Viewer sign-in refuses run_speed_scan outright, because the Hub treats it as a write, while get_speed_scan still works; the app signs in with OAuth, so the token's Read-only everywhere switch does not apply here. A job on the Scan MCP is limited to four scans per caller per ten minutes, so spread a list of competitors across separate runs. Scans started through the Scan MCP are public in the scan directory by default, and Hub scans are filed unlisted, though anyone with the link can open either. OpenAI also says the apps available to a dot may differ from ChatGPT's, so check Customize, Plugins first.

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

Yes. Ask it for a recurring check and it schedules one. Have it read the scan history with get_speed_scan each time, which spends nothing, and start run_speed_scan only when the latest report is old, because each scan spends the shared allowance.

Yes, through the xSpeed Scan MCP, which needs no account and grades any public URL read-only. Add it in developer mode beside the Hub app. It allows four scans per caller per ten minutes, and its reports are public by default.

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 ChatGPT dots

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 ChatGPT dots.

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

Open xSpeed Hub ChatGPT dots setup