# Manage every WordPress site at once with Kiro

> Managing every WordPress site at once with Kiro means asking the editor agent for one xSpeed Hub action across your whole workspace, and reading a result for each site once it returns.

Page: https://xspeedcache.com/agent/kiro/fleet/
Last updated: October 2026

You build and look after WordPress sites in Kiro, and some changes land on all of them at once: a shared plugin, a template, a new default. Instead of visiting each dashboard, you ask the agent to purge every site and start the preloader on all of them. It calls purge_cache and start_preloader with site set to "all" on the xSpeed Hub server from your MCP settings. The Hub works through your workspace one site at a time, with a one-second pause.

The result is a list with one entry per site. A site that could not be reached shows up as a failed row with its own error, and the rest are reported as done, so a mixed outcome reads as a partial success rather than a blanket result. Only seven tools accept "all": purge_cache, toggle_cache, update_settings, start_preloader, stop_preloader, optimize_site and run_benchmark. Other tools need a site name and are called once per site.

Kiro prompts before running an MCP tool unless that tool is listed in autoApprove for the server or an allow rule in your permissions covers it. The Hub also tells the agent to confirm once, with the site count, before a fleet-wide purge, toggle, settings change or preloader call, and that is an instruction to the model that does not name optimize_site. The prompt, and the connection's scope, are what actually stand between your request and a change on every site.

## Set up Kiro 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 to mcp.json

Open the command palette and run Kiro: Open user MCP config (JSON), then add this entry. The user file applies in every workspace. A project can carry its own .kiro/settings/mcp.json instead, but Kiro does not load a workspace's MCP config until you trust that workspace. Kiro reconnects servers when you save the file.

File: `~/.kiro/settings/mcp.json`

```json
{
  "mcpServers": {
    "xspeedhub": {
      "url": "https://app.xspeedcache.com/xspeed/mcp"
    }
  }
}
```

### 3. Approve access in the browser

After you save, Kiro opens the xSpeed Hub authorization page. It registers itself through dynamic client registration, so there is no client ID to create. Sign in to the Hub, approve, and check the MCP servers tab in the Kiro panel for a connected xspeedhub. There is no token to paste; Kiro keeps the credentials it receives.

Full setup: https://xspeedcache.com/agent/kiro/

### 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. Kiro prompts before it runs an MCP tool unless a rule allows it. Rules live in two places: autoApprove in the server's mcp.json entry, which lists tool names, and mcp rules in permissions.yaml, such as a match of xspeedhub/get_* with effect allow. Allow the reads and keep purge_cache, update_settings, toggle_cache and the other write tools off both lists, because the Hub itself runs a write as soon as your connection allows it. Putting "*" in autoApprove skips the prompt for every Hub tool, writes included. In a workspace you have not trusted, Kiro asks before every MCP call even when autoApprove lists the tool.

## Prompts

- Use xSpeed Hub to purge all sites and start the preloader on each, then show me any that failed.
- With xSpeed Hub, benchmark every site in my workspace and list them from the largest cached gain to the smallest.
- Ask xSpeed Hub to switch page caching on for all sites where it is currently off.

## Example session

```
You: Some sites had caching switched off during the migration. Use xSpeed Hub to turn it back on everywhere.
  → list_sites [read-only]: 9 sites in the workspace
Agent: This will touch all 9 sites and switch page caching on for each. Proceed?
You: Yes, proceed.
  → toggle_cache(site: all, enabled: true) [changes site]: 9 of 9 sites now have page caching on: 3 switched on, 6 already on
Agent: Page caching is on across all nine sites. Sites that already had it on were left as they were.
```

## 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 Kiro

Be careful what goes into autoApprove for xspeedhub. The list works by tool name, so adding purge_cache or toggle_cache to save a click on single-site work also approves their site: "all" form, and then a request to touch every site runs with no Kiro prompt at all. Put the read tools there, such as list_sites, list_workspaces and get_cache_status, and leave the write tools off the list. You still get a prompt for each fleet-wide write, and the arguments in it show whether site is a single handle or all. A star entry in autoApprove skips the prompt for every Hub tool, writes included, and a deny rule in your permissions beats an allow rule if you want a tool kept out entirely. In a workspace you have not trusted, Kiro asks before every MCP call even when autoApprove lists the tool.

## 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

### What should I put in autoApprove for xSpeed Hub in Kiro?

Read tools only, such as list_sites, list_workspaces and get_cache_status. The list is per tool name, so approving a write tool such as purge_cache also approves it for every site when the agent passes all.

### Can Kiro run a benchmark on every site without writing anything?

Yes. run_benchmark accepts all and is a read tool. It measures cached versus uncached response time on each site and returns a result per site.

### 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/) · [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/) · [Grok Bot](https://xspeedcache.com/agent/grok-bot/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 Kiro

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