How Manus handles this
Manus is built for the task you would otherwise split into a dozen steps. You run an agency and you write one request: use xSpeed Hub to check every client site, warm the ones that are cold, and give me one table. Manus lists the workspaces, runs run_benchmark with site set to "all" for the response-time picture, reads the preloader on the sites that look weak, and comes back with a plan before it changes anything, if you asked it to. Then it calls start_preloader with an array of just those handles, and the Hub returns a result for each one.
The Hub does the looping for the seven fan-out tools: purge_cache, toggle_cache, update_settings, start_preloader, stop_preloader, optimize_site and run_benchmark. It runs the sites one after another with a one-second pause and judges each site on its own, so a site that times out is one failed row and the rest are done. Any other tool, such as get_preloader_status or get_health, takes one site per call, and Manus works through those calls itself as part of the longer job. You do not need to know any tool names; naming xSpeed Hub in the task is enough for Manus to pick this server.
Manus's documentation for custom MCP servers describes no per-tool approval setting, and xSpeed Hub has no confirmation step of its own, so a fleet write runs once Manus calls it. The Hub tells the agent to confirm once, with the site count, before a purge, toggle, settings change or preloader call across every site, but it does not name optimize_site, and it is an instruction rather than a lock. Writing "ask me before changing anything" into the task, as in the session below, gives Manus a clear point to stop. The connection token is the firm control: with Read-only everywhere on, the Hub refuses every write tool sent with it.
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.
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 benchmark every site in my workspace and give me one table, slowest cached response first.
With xSpeed Hub, check the preloader on every site and warm only the cold ones, asking me once before you start.
Every Monday, use xSpeed Hub to benchmark all my sites and write me a short report. Report only.
What happens, step by step
If you run many WordPress sites, repeating one action on each is the slow part. Through xSpeed Hub, seven tools accept every site in a workspace, or a list of handles, in a single call. The Hub runs the sites one after another and returns a result for each, so a site that fails is named instead of hidden. Everything else in the Hub works on one site per call.
01
See what you can reach
list_sites returns each site's handle, URL, status and scopes. When you have more than one workspace, list_workspaces returns each one's handle, id, your role, its site count, which one is the default, and whether this connection can reach it.
02
Choose the scope of the call
The agent passes site: "all" for every site in one workspace, or an array of handles for exactly those sites. For a workspace other than the default it also passes the workspace argument. Omit workspace and the call acts on the default workspace.
03
Confirm once
Before a purge, toggle, settings change or preloader call that touches every site, the Hub tells the agent to say "this will touch all N sites" and wait for you, then make one call. That instruction does not name optimize_site, so for it your client's prompt is the gate. It is guidance to the agent, not a lock. It is one tool call, so one approval in your client covers every site in it.
04
Run it as one call
The Hub runs the sites one after another with a one-second pause between live calls, so a fleet purge is not a burst of traffic at your servers. Revoked sites are skipped from "all". Each site's action lands in the activity log as its own row.
05
Read the result per site
The reply is a summary of targets, succeeded and failed, plus one row per site with ok and either its data or its error. Some sites failing is a partial success. Only a run where every site failed comes back as an error.
06
Follow up on the failures
The agent reports which sites failed and why, then retries just those handles with an array. Tools that read one site, such as get_cache_status and get_health, do not fan out, so a fleet-wide check means one call per site.
Reference
| Fan-out tools | purge_cache, toggle_cache, update_settings, start_preloader, stop_preloader, optimize_site, run_benchmark |
|---|---|
| Selector | site: "all", or an array of handles |
| What all covers | Every site this connection can see in one workspace, minus revoked ones |
| Pacing | One after another, with a 1 second pause between live calls |
| Result | summary (targets, succeeded, failed) and a row per site: ok, then data or error |
| Partial failure | Reported per site; the call counts as an error only when every site failed |
| Workspace argument | Optional. Omit it for the default workspace; name one by its handle or id from list_workspaces |
| Reach | Fixed when you approve the connection; list_workspaces shows reachable: false for the rest |
| Not fan-out | get_health, get_cache_status and every other tool take one site per call |
| Slow tools | optimize_site takes up to 2 minutes per site; a target_score run is capped at 12 rounds per call |
| Read-only | The connection token with Read-only everywhere on, or a Viewer sign-in, refuses every fan-out write; run_benchmark works. An OAuth sign-in gets the scopes the client asks for |
| Hub daily pass | Re-verifies sites, snapshots cache status and hit ratio, reads stored reports, alerts by Slack webhook or email |
Rules worth keeping
- Confirm once, then call once. The Hub has no confirmation step of its own, so your client's approval prompt and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) are the gates that matter. The Hub's "this will touch all N sites" is an instruction to the agent for purge, toggle, settings and preloader calls, and it does not name optimize_site.
- "all" is one workspace, never every workspace. To act in another workspace, name it. A write to a non-default workspace must name it, and an array of handles is looked up only in the workspace the call names.
- Read every result per site. Treat some sites failing as a partial result, and never accept a blanket "done" from the agent.
- Try a behaviour change on one site before you send it to the fleet. toggle_cache and update_settings on every site are one call, and each site checks values against its own settings, so a Pro setting can fail on a Free site.
- optimize_site on many sites is slow, because each site can take up to two minutes inside one call. Use dry_run first, or name a short list of handles.
- The Hub has no scheduler for agent prompts. Its own daily pass and alerts run without an agent, and an agent can only act when you send a prompt or your AI client runs one on a timer.
Good to know with Manus
Scheduled tasks are where fleet work needs the most care. Manus runs them unattended on a timetable, they can use the Hub, and Scheduled Tasks 2.0 offers a skip confirmations option that lets Manus act without asking. A weekly fleet benchmark is a good scheduled task because run_benchmark is a read. A weekly purge of every site is not, because nobody is there to answer. Keep skip confirmations off, word scheduled tasks as report only, and give them a token with Read-only everywhere on. The token reaches every site in the workspace, so anyone who holds it can run a fan-out call; keep it out of chats and rotate it on the Connect AI page if it leaks, which also cuts off every other client that sends it. "All" covers one workspace, so name the client workspace in the task when you mean it, as the session above does.
More prompts for this job
They work in any client connected to xSpeed Hub.
Use xSpeed Hub to list every site I can reach, and every workspace, and say which workspace you act in by default.
With xSpeed Hub, purge the cache on every site in my workspace and tell me which ones failed.
Use xSpeed Hub to run a benchmark on all my sites and rank them by cached response time.
Use xSpeed Hub to start the preloader on blog, shop and docs only.
With xSpeed Hub, turn page caching on for every site where it is off. Check each site first.
Use xSpeed Hub to stop the preloader everywhere. The servers are busy.
Ask xSpeed Hub to preview a safe optimize_site pass on every site with dry_run and summarize what it would change.
Use xSpeed Hub to purge every site in the client-acme workspace, not my default one.
Frequently asked questions
Keep going
Manage every site at once with other agents
More with Manus
Documentation
- Managing your fleet with xSpeed Hub
- Teams, roles and workspaces in xSpeed Hub
- Scoped AI connections in xSpeed Hub
- Connecting to xSpeed Hub
- How to write prompts for xSpeed Hub
- Manus + xSpeed
- Every AI agent that works with xSpeed
From the blog