# Manage every WordPress site at once with Grok Bot

> Managing every WordPress site at once with Grok Bot means asking a named xAI Bot, on its own cloud computer, to run one xSpeed Hub action across the workspace, now or as a routine, and report on each site.

Page: https://xspeedcache.com/agent/grok-bot/fleet/
Last updated: October 2026

A Grok Bot keeps its context and works on a persistent cloud computer, so it can own a standing job such as keeping an eye on twelve client sites. You attach the xspeedhub plugin with @ in a chat and ask for a fleet action. For a picture of the whole workspace, the Bot calls run_benchmark with site set to "all", and the Hub measures each site's cached and uncached response time in turn, one second apart. For a change, such as clearing every cache after a shared template update, it calls purge_cache the same way. Either call returns one row per site with ok and either data or an error.

Routines are where a Bot differs from a chat. You tell the Bot when to run, what to check and what it must not do, it creates the routine and shows the next run, and background routines keep going while your laptop is closed. The Hub has no scheduler for agent prompts, so the timer is the Bot's. A routine that benchmarks every site each weekday is a good fit, because run_benchmark is a read. A routine that purges or toggles every site is not, because nobody is there to say yes, and xAI notes that even a Test run performs real work against connected tools.

When an action needs approval, Grok Bot offers Allow once, Always allow or Deny. Always allow saves a rule, and a rule on purge_cache covers its site: "all" form as well as a single site. Auto-review rules under Settings, General, Auto-review can force Ask first for named actions, and Ask first wins over an automatic allow when both match. xSpeed Hub has no confirmation step of its own, and its instruction to confirm once before a fleet-wide purge, toggle, settings or preloader call is guidance to the model that does not name optimize_site.

## Set up Grok Bot 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. Ask your Bot to add xSpeed Hub

In a chat with your Bot, ask it to add a custom remote HTTPS MCP server with this URL. xAI says a plugin you add from your own chat is personal and account-wide, so every Bot on your account can use it. When the browser opens, approve access on the xSpeed Hub page.

```
Add a custom remote HTTPS MCP server called xspeedhub with the URL https://app.xspeedcache.com/xspeed/mcp and sign me in.
```

### 3. Attach it and ask a first question

Type @ in a chat to attach the xspeedhub plugin to the task, then ask something that names xSpeed Hub. A list of your sites means the connection works.

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

Full setup: https://xspeedcache.com/agent/grok-bot/

### 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. When an action needs approval, Grok Bot offers Allow once, Always allow or Deny. Always allow saves a rule, so the same kind of call no longer stops for you. Auto-review rules under Settings, General, Auto-review can force Ask first or allow matching actions automatically, and Ask first wins when both match. xSpeed Hub has no confirmation step of its own, so a Hub write tool you always allow runs as soon as your connection allows writes. Add Ask first rules for purge_cache, update_settings, toggle_cache, optimize_site and the other write tools. For read-only access, sign in as a Viewer member of the workspace.

## Prompts

- Every weekday at 7:00, use @xspeedhub (xSpeed Hub) to benchmark every site and post one line per site. Report only.
- With xSpeed Hub, purge every site in my workspace after this template change and list any that failed.
- Use xSpeed Hub to stop the preloader on every site while the hosts are under load, then confirm each one is idle.

## Example session

```
You: Use @xspeedhub (xSpeed Hub) to clear every site's cache. The shared template changed.
  → list_sites [read-only]: 12 sites in the workspace
Agent: This will touch all 12 sites with a full purge. Allow it?
You: Allow once.
  → purge_cache(site: all, type: all) [changes site]: 12 of 12 purged
Agent: All twelve sites are clear. They refill as visitors arrive, or I can start the preloader on all of them now. Start it?
You: Start it.
  → start_preloader(site: all) [changes site]: 11 started; staging-k refused, preloader off
Agent: Warming on eleven sites. staging-k has the preloader module switched off, so it stays cold until a visitor arrives.
```

## How it works

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

- 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 Grok Bot

Add Ask first rules for the six fan-out tools that write (purge_cache, toggle_cache, update_settings, start_preloader, stop_preloader and optimize_site) before you write your first routine, and resist Always allow on any of them, because that grant covers every site in the workspace in one call. A plugin you add from your own chat is personal and account-wide, so every Bot on your account can reach all of your sites through it. If only one Bot should, use a Team Bot whose owner adds the plugin in its Setup panel, where each teammate signs in to xSpeed Hub with their own account and their own role. The sign-in is OAuth, so the Hub's Read-only everywhere switch does not apply; a Viewer member's sign-in is the read-only route, and it still allows a fleet benchmark. On a team plan, xAI says Grok Bot inherits your team's Cursor connector policy, so a blocked Hub shows as Disabled by team admin until an admin allows it.

## 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

### Can a Grok Bot watch all my sites while I am away?

Yes, with a routine. Ask the Bot to benchmark every site on a schedule and it runs on its cloud computer even with your laptop closed. Keep routines to reads such as run_benchmark, because nobody is there to approve a purge.

### What does Always allow on purge_cache mean for my fleet?

It saves a rule for that tool, so later calls skip the prompt, including a call with site set to all that purges every site in the workspace. Keep Ask first rules on the fan-out write tools instead.

### What does site "all" cover?

Every site the connection can see in one workspace. It never crosses workspaces, and revoked sites are skipped. If your connection is limited to some sites, "all" quietly means the sites you are allowed, with no error naming the rest. To act in another workspace, the agent names it with the workspace argument.

### What happens if one site fails?

The other sites still run. The reply has a summary and a row for each site with ok and its data or its error, so a site that was unreachable is named. A run counts as an error only when every site failed. Ask the agent to retry just the failed handles.

### Can the agent check the health of every site in one call?

No. get_health and get_cache_status take one site per call, so the agent loops. The tools that fan out are purge_cache, toggle_cache, update_settings, start_preloader, stop_preloader, optimize_site and run_benchmark. The Hub dashboard has a fleet overview for health.

### Does the Hub watch my fleet when no agent is running?

Yes, on its own. A daily pass re-verifies each site, retrying a failed probe once, snapshots cache status and hit ratio, and reads the PageSpeed and GTmetrix reports your sites already stored. It can alert you by Slack webhook or email when a site becomes unreachable, caching is switched off, the hit ratio falls below a floor you set, or a score regresses. Each alert fires once per incident, not every day.

### Does the Hub ask before it touches every site?

The Hub has no confirmation step. Its instructions tell the agent to confirm once with you, saying how many sites a call will touch, but that is guidance and not a lock. Your AI client's approval prompt and a read-only connection (the connection token with Read-only everywhere on, or a Viewer sign-in) are what stop a write. The instruction covers purge, toggle, settings and preloader calls, not optimize_site. The dashboard's own Purge all button does confirm before it runs.

### Can the agent add sites, remove sites or change who has access?

No. It cannot add, remove or rename sites, change members, roles or billing, mint or rotate tokens, or widen the workspaces this connection reaches. Those stay in the Hub dashboard.

## Manage every site at once with other agents

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

## More with Grok Bot

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

## Documentation

- Managing your fleet with xSpeed Hub: https://xspeedcache.com/docs/managing-your-fleet-with-xspeed-hub/
- Teams, roles and workspaces in xSpeed Hub: https://xspeedcache.com/docs/hub-teams-and-workspaces/
- Scoped AI connections in xSpeed Hub: https://xspeedcache.com/docs/hub-connection-scopes/
- Connecting to xSpeed Hub: https://xspeedcache.com/docs/connecting-to-xspeed-hub/