# Manage every WordPress site at once with Antigravity

> Managing every WordPress site at once with Antigravity means asking the editor agent for one xSpeed Hub action across your whole workspace and reading what happened on each site when it returns.

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

You build or maintain several WordPress sites in Antigravity, and the agent panel is the quickest way to say "do this everywhere". You ask for a purge and a re-warm after a release. The agent calls purge_cache and then start_preloader with site set to "all" on the xSpeed Hub server, and the Hub works through the sites in your workspace, one after another with a one-second pause between them.

The reply is a result for each site, not a merged status. If nine sites clear and one is unreachable, the agent should say nine and one, and name the site and the error. A fan-out call is a partial success when some sites fail. Only seven tools accept "all": purge_cache, toggle_cache, update_settings, start_preloader, stop_preloader, optimize_site and run_benchmark. For all other tools, such as reading a site's settings, the agent has to name the site.

Antigravity runs unconfigured MCP tools in Ask mode, so each call waits for your approval in a card before it executes. An allow rule such as mcp(xspeedhub/purge_cache) lets a call through without a prompt, and the Turbo permission preset allows MCP actions without asking. For a purge, toggle, settings change or preloader call, the Hub tells the agent to confirm once with the site count, but that is guidance to the model and not enforcement, and it does not name optimize_site. The one control the Hub enforces is the connection's scope: with the connection token and Read-only everywhere on, or a Viewer sign-in, every write tool is refused.

## Set up Antigravity 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_config.json

Antigravity reads ~/.gemini/config/mcp_config.json for every project, or .agents/mcp_config.json inside one workspace. In the IDE, open the ... menu at the top of the agent side panel, choose MCP Servers, then Manage MCP Servers and View raw config. Remote servers must use the serverUrl field; the older url and httpUrl fields are not supported.

File: `~/.gemini/config/mcp_config.json`

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

### 3. Authenticate

Open Agent settings with Cmd+, on macOS or Ctrl+, on Windows and Linux, go to the Customizations tab and click Authenticate next to xspeedhub. Sign in to xSpeed Hub in the browser and approve access, copy the authorization code the page shows, paste it into the settings panel and click Submit. Antigravity keeps the credentials it receives and refreshes them. In the CLI, type /mcp to open the MCP manager and check the server status.

```
Settings → Customizations → Authenticate
```

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

### 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. Antigravity runs unconfigured MCP tools in Ask mode, so each call waits for your approval in a card before it executes. Allow rules such as mcp(xspeedhub/get_cache_status) or mcp(xspeedhub/*) let calls through without a prompt, Ask and Deny rules take precedence over Allow, and the Turbo permission preset allows MCP and web actions without asking. When you approve a card you can also edit its target to widen the grant. With Turbo or a broad allow rule, a write reaches the Hub as soon as your connection allows writes. xSpeed Hub has no confirmation step of its own.

## Prompts

- Use xSpeed Hub to purge every site and re-warm all of them, then list the sites that failed.
- With xSpeed Hub, benchmark all sites and tell me which have the smallest cached-versus-uncached improvement.
- Ask xSpeed Hub to list my workspaces, then run the benchmark on every site in the agency workspace.

## Example session

```
You: Use xSpeed Hub to list my workspaces and benchmark every site in the agency one.
  → list_workspaces [read-only]: 2 workspaces: personal (4 sites), agency (11 sites)
  → run_benchmark(site: all, workspace: agency) [read-only]: 10 benchmarked; client-k unreachable
Agent: Ten of the eleven agency sites were measured. client-k did not respond, so I have no figures for it. The personal workspace was not included, because all covers one workspace.
```

## 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 Antigravity

Under the Turbo preset, or with an allow rule for a write tool or the whole xspeedhub server, a fleet write reaches the Hub as soon as your connection allows writes, and the approval card lets you edit its target to widen a grant, so read what you are widening before you click. Take the cautious route for fleet work: connect through a read-only connection first and use it for benchmarks and reports, and only mint a write connection when you need a fan-out change. The Connect AI page in the Hub has the Read-only everywhere switch for the connection token. Keep in mind that a write to a workspace other than your default must name the workspace, so read the call before it runs. If the arguments show a single handle where you expected all, or the reverse, stop and say so before approving.

## 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 Antigravity act on all my sites?

Yes, for the seven fan-out tools. The agent sends one call with site set to all and the Hub runs each site in turn. For a workspace other than your default, a write has to name the workspace.

### Is there a safe way to try fleet actions in Antigravity?

Use a read-only connection token, with Read-only everywhere on. run_benchmark accepts all and is a read tool, so you can measure every site and see how the per-site results look before you allow a write.

### 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/) · [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/) · [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 Antigravity

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