How Manus handles this
Manus takes a whole task to a finished result, and a quarterly speed review across an agency's sites is that kind of task. You ask it to use xSpeed Hub to review the speed of every site, rescan anything older than two weeks, and give you one table with the desktop and mobile grades and the top fix for each. Manus calls get_speed_scan on each site to read its history for free, starts run_speed_scan only on the sites whose latest report is stale, and assembles the brief with a report link per site.
Each scan grades out of 100 from server probes and a Lighthouse run, with the desktop run as the headline and the mobile run graded beside it, and the failing checks ranked by points recoverable. The Hub waits about 50 seconds for a scan; when one is still running it returns a scan id, and Manus polls get_speed_scan with it before moving on. A brief built this way compares like with like only if every row graded the full rubric, so ask Manus to mark any scan that lost its Lighthouse run as partial.
This page stays on the Hub route. Manus documents a credential, such as an API key or a Bearer token, for a custom MCP server, and you give it the Hub's connection token. The Hub classes run_speed_scan as a write tool because each scan spends the shared speed-test allowance, so on a token with Read-only everywhere on, the Hub refuses it and Manus can only read history. Manus's custom MCP documentation describes no per-tool approval setting, and xSpeed Hub has no confirmation step of its own, so writing a scan budget into the task is how you keep a review from spending more than you meant.
Set up Manus once
Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Manus 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.
2Copy the connection token from xSpeed Hub
Sign in at app.xspeedcache.com as the workspace owner, open Connect AI and copy the connection token. If Manus will only report, turn on Read-only everywhere so the Hub refuses every write tool on that token.
xSpeed Hub > Connect AI > connection token
3Add xSpeed Hub as a custom MCP server
In Manus, open Settings, then Integrations, then Custom MCP Servers, and click Add Server. Name it xSpeed Hub, enter this as the server URL, and enter the connection token as the Bearer token in the authentication field.
https://app.xspeedcache.com/xspeed/mcp
4Let Manus test it, then name it in a task
Manus checks that it can reach the server and read its list of tools. Then start a task that names xSpeed Hub, so Manus uses this server.
Use xSpeed Hub to list my sites and tell me which ones have page caching turned off.
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 Manus 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 Manus 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. Manus's custom MCP documentation describes no per-tool approval setting for a custom server, and its scheduled tasks offer a skip confirmations option that lets Manus act without asking each time. xSpeed Hub has no confirmation step of its own, so a write runs as soon as Manus 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. The firm stop is the token: with Read-only everywhere on, the Hub refuses every write tool. Keep it on for scheduled work, and leave skip confirmations off for any task that may write.
What do I ask?
Three prompts written for Manus. More for this job are below.
Use xSpeed Hub to review the speed of every site and rescan only those whose latest report is over two weeks old. At most three scans.
With xSpeed Hub, read blog's scan history and tell me whether its mobile grade has gone up or down this quarter.
Every Monday, use xSpeed Hub to read the latest scan for each site and write me a one-table brief. Do not start new scans.
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.
01
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.
02
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.
03
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.
04
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.
05
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.
06
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 Manus
A scheduled review is the natural next step, and Manus runs scheduled tasks unattended on a timetable. A weekly task that only reads history works on a read-only token and spends nothing. A task that must start scans needs Read-only everywhere off, which also lets anything holding the token purge or change settings on every site, so give that task a plain budget in its wording (at most three scans, only where the report is over two weeks old) and keep the skip confirmations option off. A scan cannot reach private, local or password-protected sites, so a staging site behind a login returns an error instead of a grade. Hub scans are filed unlisted, which keeps them out of the public scan directory, but a report link in a brief opens for anyone who receives it. Rotating the token cuts off Manus and every other client that sends 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
Keep going
Scan a site's speed with other agents
More with Manus
Documentation
- xSpeed Scan: free website speed test
- xSpeed Scan MCP: speed-test any site from your AI assistant
- How to run a full site scan
- Running speed tests in xSpeed Hub
- How to write prompts for xSpeed Hub
- Manus + xSpeed
- Every AI agent that works with xSpeed
From the blog