# ChatGPT + xSpeed: Manage WordPress Caching

> ChatGPT is OpenAI's AI assistant, and in developer mode on the web it can use xSpeed Hub as a custom MCP app to read cache status, purge, change settings and run speed tests on your WordPress sites from a chat. You register the Hub's URL once, sign in, and pick the app from the composer.

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

- One app URL, every site you connected to the Hub
- ChatGPT shows each tool call as a confirmation you can expand and read
- Web only: custom MCP apps are not available in the mobile apps

## How do I connect ChatGPT to xSpeed?

### 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. Turn on developer mode

In ChatGPT on the web, open Settings, then Security and login, and turn on Developer mode. On a Business workspace only admins and owners can use it. On Enterprise and Edu an admin grants access first, and you then turn it on under Settings, Apps, Advanced settings.

```
Settings  >  Security and login  >  Developer mode
```

### 3. Create the app from the Hub URL

Open ChatGPT Plugins, select the plus button and create a developer-mode app. Name it xspeedhub, paste the MCP server URL and choose OAuth. Click Scan Tools, approve access on the xSpeed Hub page that opens, wait for the scan to list the tools, then click Create. Workspace admins can also start from Workspace settings, Apps, Create.

```
https://app.xspeedcache.com/xspeed/mcp
```

### 4. Select the app in a chat

The app appears under Drafts in your app settings with a Dev label. In a new chat, open the plus menu in the composer, choose Developer mode and select xspeedhub. In a workspace, only an admin or owner can publish the app for other members.

```
+  >  Developer mode  >  xspeedhub
```

**Authentication:** OAuth sign-in. ChatGPT custom apps take OAuth, no authentication or a mix of the two, and have no header field, so the connection token does not apply here. Pick OAuth and approve access on an xSpeed Hub page.

**Check it worked:** ask "Use the xspeedhub app to list my xSpeed sites and tell me which ones have page caching turned off. Do not change anything."

## Does ChatGPT ask before it changes my site?

ChatGPT asks you to confirm write actions by default. You can expand a tool call to read the JSON it will send, and you can choose to remember an approve or deny choice for a tool for the rest of that conversation. ChatGPT respects a tool's read-only annotation and treats a tool without one as a write action; xSpeed Hub's tool definitions do not declare that annotation today, so expect confirmations on reads as well. OpenAI says confirmation also depends on app permissions and context, and some especially risky actions can be blocked. xSpeed Hub has no confirmation step of its own, so once you tell ChatGPT to remember Approve for a tool, that tool runs without a prompt for the rest of the conversation, as soon as your connection allows writes.

xSpeed Hub has no confirmation step of its own. Read tools change nothing on your sites, with one exception to know about: contact_support sends an email to xSpeed support, and a read-only connection can still call it. A write tool (a purge, a settings change, a cache toggle, or a speed test that spends the shared allowance) runs as soon as your connection allows writes. Three things stand between a prompt and a change: your connection's scope, because a read-only connection refuses every write tool (the connection token has a Read-only everywhere switch, and a Viewer member only ever gets read access); your AI client's own tool-approval prompt; and the Hub's instructions to the agent, which tell it to confirm the target site and to ask once before a write that touches every site.

## Example session

```
You: Use the xspeedhub app. Which of my sites has page caching turned off?
  → list_sites [read-only]: 5 sites: shop, blog, docs, agency, staging
  → get_cache_status(site: shop) [read-only]: page cache on, 412 cached pages
  → get_cache_status(site: blog) [read-only]: page cache on, 230 cached pages
  → get_cache_status(site: docs) [read-only]: page cache on, 96 cached pages
  → get_cache_status(site: agency) [read-only]: page cache on, 58 cached pages
  → get_cache_status(site: staging) [read-only]: page cache off, 0 cached pages
Agent: Only staging has page caching off; the other four have it on. Turning it on changes that site's settings. Should I turn it on?
You: Yes, turn it on.
  → toggle_cache(site: staging, enabled: true) [changes site]: page cache turned on for staging
Agent: Page caching is on for staging. It starts empty, so the first visits will fill the cache. I can start the preloader if you want it warmed.
```

## What is ChatGPT?

ChatGPT is OpenAI's AI assistant. Its developer mode gives ChatGPT on the web full MCP client support for custom apps, including write tools, so a chat can call tools on a remote MCP server that you register.

MCP, the Model Context Protocol, is how those tools are described to the model. Registering xSpeed Hub as an app gives ChatGPT the Hub's caching tools for every site in your workspace. OpenAI labels developer mode as elevated risk and warns about prompt injection and model mistakes on write actions. ChatGPT signs in with OAuth and gets the scopes it asks for, which are read and write. The Hub's Read-only everywhere switch applies only to the connection token, which ChatGPT cannot send, so for read-only access sign in as a Viewer member of the workspace.

## Why use ChatGPT with xSpeed?

- **A confirmation you can read**: ChatGPT shows each tool call with its input and output. Expand it before you approve a purge or a settings change, and see exactly which site and which options it will send.
- **Reads and writes in the same chat**: Ask for the status, hear the diagnosis and approve the fix in one conversation. The agent lists your sites first, so you can name a site in plain words.
- **Share it with a workspace**: On Business, Enterprise and Edu plans an admin can publish the app so members can use it, and Enterprise and Edu admins can switch individual tools on or off after publishing.

## Good to know

- Plan limits differ between OpenAI pages. The developer-mode guide lists Pro, Plus, Business, Enterprise and Edu on the web, while the help center describes full MCP with write actions as a beta for Business, Enterprise and Edu and says Pro connects with read access. If the Hub's write tools are missing, check your plan with OpenAI.
- Custom MCP apps are web only. OpenAI says agent mode does not use custom apps, and deep research uses them for read and fetch only, not writes.
- OpenAI notes that OAuth connections can lose access and ask you to reauthenticate when the provider does not advertise the offline_access scope. The Hub lists the scopes read and write. If ChatGPT asks you to sign in again, approve access again.
- After an admin publishes an app, ChatGPT works from a snapshot of its tools. If the Hub adds tools later, an admin refreshes the actions in Workspace settings.

## Prompts to try

- Use the xspeedhub app: show the cache hit ratio for every site and flag anything under 70%.
- Use the xspeedhub app to purge the page cache on the blog site, then tell me what it cleared.
- Use xspeedhub to run a mobile PageSpeed test on shop and compare it with the score history.
- Use xspeedhub to check whether Redis is reachable on shop before suggesting the object cache.
- Use xspeedhub, read only: which of my sites has an unwarmed cache?

## What can ChatGPT do with xSpeed?

- [Purge the WordPress cache with ChatGPT](https://xspeedcache.com/agent/chatgpt/purge-cache/): Clear stale pages after a deploy, an edit or a plugin update, on one site or all of them.
- [Find out why WordPress pages are not cached with ChatGPT](https://xspeedcache.com/agent/chatgpt/troubleshoot-cache/): Work out why a site misses the cache, serves slow pages or shows a low hit ratio, using read-only checks first.
- [Scan a website for speed problems with ChatGPT](https://xspeedcache.com/agent/chatgpt/speed-scan/): Get a graded speed report with the fix for every failing check and a link you can share, for your own site or any public URL.
- [Run and track PageSpeed tests with ChatGPT](https://xspeedcache.com/agent/chatgpt/pagespeed-tests/): Read the PageSpeed scores a site already has, run a new test when something changed, and tell a Lighthouse score from a cache benchmark.
- [Raise a WordPress site's PageSpeed score with ChatGPT](https://xspeedcache.com/agent/chatgpt/optimize-site/): Preview and apply xSpeed's recommended settings to a site, check the pages still work, and be told plainly what caching cannot fix.
- [Tune WordPress cache settings with ChatGPT](https://xspeedcache.com/agent/chatgpt/cache-settings/): See which modules a site has, read their current settings, change them, and turn page caching on or off.
- [Warm the WordPress cache with ChatGPT](https://xspeedcache.com/agent/chatgpt/preload-cache/): Fill the page cache before visitors arrive, for example right after a purge or a deploy.
- [Set up the Redis object cache with ChatGPT](https://xspeedcache.com/agent/chatgpt/object-cache/): Connect a site to Redis or Memcached so database results survive between requests.
- [Manage Cloudflare caching with ChatGPT](https://xspeedcache.com/agent/chatgpt/cloudflare/): Check the Cloudflare connection, clear the edge cache and switch development mode on or off for a site.
- [Manage every WordPress site at once with ChatGPT](https://xspeedcache.com/agent/chatgpt/fleet/): Run one action across all of your sites, or a chosen few, and read the result site by site.

## Which way should I connect?

| Surface | Endpoint | Reaches | Auth | Tools |
| --- | --- | --- | --- | --- |
| [xSpeed Hub MCP](https://xspeedcache.com/docs/hub-mcp/) | `https://app.xspeedcache.com/xspeed/mcp` | Every site in your workspace, one connection | OAuth sign-in in the browser, or a connection token in an Authorization header | 29 tools (16 read, 13 write), seven of them can act on every site at once |
| [xSpeed Cache Site MCP](https://xspeedcache.com/docs/mcp-server/) | `https://your-site.com/xspeed/mcp` | One WordPress site | OAuth sign-in by a site admin, or the site's own token in an Authorization header | The full per-site tool set plus run_command for the WP-CLI surface |
| [xSpeed Scan MCP](https://xspeedcache.com/docs/scan-mcp/) | `https://xspeedcache.com/scan/mcp` | Any public URL, read-only | None. No account. | 5 tools: run_speed_scan, get_speed_scan and three product-info tools |
| [WP-CLI](https://xspeedcache.com/docs/wp-cli-commands/) | `wp xspeed …` | The site whose server the agent has a shell on | Your server login | Every xSpeed command: cache, purge, preloader, objcache, cf, score, settings and more |

## Frequently asked questions

### How do I add xSpeed Hub to ChatGPT?

Turn on Developer mode under Settings, then Security and login. Open ChatGPT Plugins, select the plus button, name the app, paste https://app.xspeedcache.com/xspeed/mcp, choose OAuth, click Scan Tools, approve access on the xSpeed Hub page and click Create. Then pick Developer mode and the app from the plus menu in a chat.

### Do I need an API key?

No. ChatGPT signs in to the Hub with OAuth and keeps the credentials it receives. ChatGPT custom apps accept OAuth, no authentication or a mix, and have no field for a header, so the Hub's connection token is not used here.

### Will ChatGPT change my site without asking?

ChatGPT asks for confirmation on write actions by default, and the Hub's tools carry no read-only annotation, so you will usually be asked for reads as well. You can tell ChatGPT to remember an approval for a tool for the rest of a conversation, and after that the tool runs without a prompt. The Hub has no confirmation step of its own, and its Read-only everywhere switch does not apply to an OAuth sign-in. For read-only access, sign in as a Viewer member of the workspace, or keep ChatGPT's own confirmations on.

### Does it work on the ChatGPT mobile app?

No. OpenAI says custom MCP apps are web only. Use the web version of ChatGPT to reach the Hub.

### Which ChatGPT plans can use it?

OpenAI's pages differ. The developer-mode guide lists Pro, Plus, Business, Enterprise and Edu accounts on the web. The help center says full MCP support with write actions is a beta for Business, Enterprise and Edu, and that Pro accounts connect with read and fetch permissions. If you only get the Hub's read tools, that is the likely reason.

### Who can set it up for a whole team?

On Business workspaces, admins and owners enable developer mode, create the app and publish it. On Enterprise and Edu, admins grant developer access with roles, publish the app and choose which actions members can use. Members then pick the app in chats.

### Why does ChatGPT stop reaching the Hub and ask me to sign in again?

OpenAI notes that an OAuth connection can lose access when the provider does not advertise the offline_access scope, and the Hub lists the scopes read and write. Approve access again when ChatGPT asks. If it keeps happening, remove the app and create it again.

### How do I disconnect ChatGPT?

Remove the app you created in ChatGPT, or ask a workspace admin to remove the published app. Rotating or disconnecting the Hub's connection token does not end this sign-in, because ChatGPT uses OAuth and not that token. The OAuth sign-in is removed on the ChatGPT side.

## Also works with

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

## Sources

- OpenAI Developers: ChatGPT developer mode: https://developers.openai.com/api/docs/guides/developer-mode
- OpenAI Help Center: Developer mode and MCP apps in ChatGPT: https://help.openai.com/en/articles/12584461-developer-mode-and-mcp-apps-in-chatgpt