Set up the Redis object cache with Antigravity

Setting up a Redis object cache with Antigravity means asking its agent in the editor to check a site's object cache, test the Redis connection and enable it through xSpeed Hub.

get_object_cache_statustest_object_cacheget_settingsupdate_settingstoggle_object_cacheflush_object_cache

Last updated: October 2026

Example session · Antigravity

You: Use xSpeed Hub to set up Redis for shop. Name each tool before you call it.

Antigravity: Order: get_object_cache_status, test_object_cache, then toggle_object_cache only if the test passes and you agree.

get_object_cache_status(site: shop) read-only
→ Drop-in not installed. Backend: Redis configured.

test_object_cache(site: shop) read-only
→ Connected. Probe value written and read back.

Antigravity: Redis answers. Enable the object cache on shop now?

You: Yes, enable it.

toggle_object_cache(site: shop, enabled: true) changes site
→ Drop-in installed. Redis active.

How Antigravity handles this

You are in Antigravity, the Google editor, with the agent panel beside your WordPress project, and the site's database queries are what slow it down. Type: set up Redis for shop and run the connection test before enabling. The agent calls get_object_cache_status through xSpeed Hub and reports whether the object-cache.php drop-in is installed, which backend is configured and its stats. That read does not show whether Redis answers.

The next call is test_object_cache, where the site's plugin connects to its Redis server and reads and writes a probe value. A failure returns the server's own error, and then the work is on the host side, not in the editor. Only a pass leads to toggle_object_cache with enabled set to true, which installs the drop-in. The site tests the connection again when you enable and writes nothing if it fails, but the probe you ran first names the cause, so the test comes first every time. Enabling also writes the connection constants into wp-config.php.

What differs for Antigravity is its permission model. MCP tools it has no rule for run in Ask mode, so each call waits for your approval in a card. Allow rules such as mcp(xspeedhub/get_object_cache_status) and mcp(xspeedhub/test_object_cache) let the two reads through, Deny and Ask rules beat Allow, and the Turbo preset allows MCP actions without asking. The Hub has no confirmation step of its own. The editor runs on your machine, so the Redis check comes from the site through the test tool, not from a local terminal.

Set up Antigravity once

Already connected? Skip to the prompts. Alternatives and troubleshooting are on the Antigravity 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.

2Add 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.

~/.gemini/config/mcp_config.json

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

3Authenticate

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.

Text

Settings → Customizations → Authenticate

1 / 3

Full Antigravity 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. 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.

What do I ask?

Three prompts written for Antigravity. More for this job are below.

Prompt for Antigravity

Before you call anything, list the xSpeed Hub object cache tools you will use for shop and in what order.

Prompt for Antigravity

Use xSpeed Hub to check the object cache status on shop, run the Redis test, and wait for me to say go.

Prompt for Antigravity

Using xSpeed Hub, wait for a passing Redis test on shop, then enable the object cache and read the status back.

What happens, step by step

A persistent object cache keeps database query results in Redis or Memcached instead of rebuilding them on every request. Through xSpeed Hub an agent can read the state of the cache, probe the cache server, switch the cache on or off, and flush it. The Hub tells the agent to run the probe first, because the status call alone does not prove the server is reachable.

Read the current state

get_object_cache_status reports whether the object-cache.php drop-in is installed, which backend is configured, Redis or Memcached, and its stats. It does not prove the server answers, so a clean status is not a green light.

Test the connection first

test_object_cache opens a live connection to the configured server and does a read and write probe with the settings saved on the site. A failure comes back with the server's own reason, such as a wrong password, a refused connection or a permission error. The Hub tells the agent to run this before toggle_object_cache.

Fix the connection if the test fails

get_settings reads the object-cache module, with secrets masked. update_settings changes it, for example the host or port. On a managed host that defines these values in wp-config.php, the fields are read-only and a write that tries to change one is refused with the name of the constant. For a host that wants the constants pasted, get_object_cache_status with detail set to snippet returns the wp-config.php block.

Turn it on

toggle_object_cache with enabled true makes the site test the connection again, write the connection constants into wp-config.php and install the object-cache.php drop-in. If the test fails, it stops with "Could not enable" and writes nothing. If wp-config.php is not writable, the drop-in goes in and the reply tells you to add the snippet by hand. The Hub tells the agent to briefly confirm intent first.

Check it took

The drop-in loads on the next request, so the agent reads get_object_cache_status again after a page load and runs test_object_cache once more. The status also warns when the cache connects but refuses writes, so a connected cache that stores nothing does not pass as healthy.

Flush when stale data survives

flush_object_cache empties the persistent object cache. Use it when old options, transients or query results outlive a page cache purge. It does not touch the page cache; purge_cache does that.

Reference

Read tools	get_object_cache_status and test_object_cache, both work on a read-only connection
Write tools	toggle_object_cache (enabled true or false) and flush_object_cache
Backends	Redis or Memcached
Status detail	status (default) or snippet, the wp-config.php constants block
What status proves	Drop-in installed, backend configured, stats. Not that the server is reachable
What the test proves	A live connect and a read and write probe on the saved settings, with the server's own error on failure
Enable does	Tests the connection, writes connection constants to wp-config.php, installs the object-cache.php drop-in
Disable does	Removes xSpeed's drop-in and its wp-config.php block; a drop-in owned by another plugin is left alone
Connection timeout	1 second by default, set in the object-cache module
Settings module	object-cache, for get_settings and update_settings
Every site at once	None of these tools accept site: "all"; one site per call
Confirmation	None on the Hub; your client's prompt is the gate

Rules worth keeping

Test before you toggle. The Hub tells the agent to run test_object_cache first, because a cache server that does not answer slows every request while the page cache still looks healthy.
Keep the Redis password out of the chat. get_settings masks it, but the wp-config.php snippet is built from the saved settings and can include a saved password. Set secrets in wp-config.php or in the xSpeed panel.
toggle_object_cache and flush_object_cache are write tools. The Hub tells the agent to briefly confirm intent for the object-cache toggles, but that is guidance, not a lock. Your client's approval prompt and a read-only grant are the gates that matter. A read-only grant means the connection token with Read-only everywhere on, or a Viewer member's sign-in; an OAuth sign-in gets the scopes the client asks for, which are read and write by default.
If another plugin owns the object-cache.php drop-in, turn its object cache off in that plugin. xSpeed leaves a drop-in it did not install in place when you disable.
A flush clears cached data, so the next requests rebuild it from the database and the site is briefly slower. Flush one site, then check it, before you repeat it.

Good to know with Antigravity

The Turbo permission preset allows MCP and web actions without asking, so under Turbo toggle_object_cache runs as soon as the agent calls it. If you use Turbo, add an Ask rule for toggle_object_cache and flush_object_cache, or use the connection token with Read-only everywhere on while you diagnose. When you approve a card you can edit its target to widen the grant, so read the target before you accept it for a write.

More prompts for this job

They work in any client connected to xSpeed Hub.

Prompt

Using xSpeed Hub, is a persistent object cache running on shop, and which backend does it use?

Prompt

Use xSpeed Hub to test whether Redis is reachable from shop. Do not change anything.

Prompt

Shop is slow in wp-admin. Use xSpeed Hub to check the object cache before anything else.

Prompt

With xSpeed Hub, test Redis on shop, and if it passes, turn the object cache on.

Prompt

Ask xSpeed Hub for the wp-config.php object cache snippet for docs.

Prompt

Use xSpeed Hub to flush the object cache on blog. Old options survive a page cache purge.

Prompt

With xSpeed Hub, turn the object cache off on shop and confirm the drop-in is gone.

Frequently asked questions

By default, yes. MCP tools with no rule run in Ask mode and wait for your approval in a card. The Hub has no confirmation step of its own, so an allow rule that covers the toggle, or the Turbo preset, lets the write run without a prompt. The one gate that always holds is the connection token with Read-only everywhere on, or a Viewer sign-in, because the Hub then refuses every write.

Report the Redis server error and stop. A failed test means the backend is not answering with the current settings, and the site will refuse to enable too, so fix the host side and run the test again before any toggle.

Because a cache server that does not answer costs time on every request while the page cache still looks fine. The Hub tells the agent to run test_object_cache first, and the site also tests the connection when you enable and refuses to continue if it fails. The probe is still worth running on its own, since it returns the server's exact reason, such as a wrong password or a refused connection.

The site keeps working. The drop-in is built never to take the site down: it falls back to WordPress's own cache for the length of the request and marks itself as degraded. A request can still wait up to the connection timeout, which is 1 second by default, so the site gets slower. xSpeed reports that state as degraded, and test_object_cache names the fault.

No. These tools connect xSpeed to a Redis or Memcached server that already exists and switch the object cache on or off. Getting a server is a hosting task. xSpeed uses the phpredis extension when it is there and its own built-in client when it is not.

flush_object_cache empties the persistent object cache and nothing else. purge_cache with type object does the same job through the purge tool, and purge_cache with type all also clears the page cache and, when connected, the Cloudflare edge. Use the flush when stale options or transients survive a page cache purge.

Treat it like a secret. The snippet is built from the settings saved on the site, so it can contain the Redis password if one is saved. Paste it into wp-config.php yourself and avoid sharing it in a chat or a ticket.

Set up Redis object cache, from Antigravity.

xSpeed Hub is free and has no site cap. Connect your sites once and ask from the agent you already use.

Open xSpeed Hub Antigravity setup

Set up the Redis object cache with Antigravity

How Antigravity handles this

Set up Antigravity once

What do I ask?

What happens, step by step

Reference

Rules worth keeping

More prompts for this job

Frequently asked questions

Keep going

Set up Redis object cache, from Antigravity.