Black Friday: 50% off every paid plan. Lifetime from $79.

Grab 50% Off Grab it →
Get Plugin xSpeed Hub
xSpeed Hub Pricing Docs Blog Scan
Appearance
Get Plugin
All articles
MCPAIxSpeed HubPageSpeedTutorial

How to Let Claude or ChatGPT Manage Your WordPress Site Speed (via MCP)

Updated Oct 27, 2026 12 min read
Let Claude or ChatGPT manage site speed, with the Claude, OpenAI and WordPress logos, xSpeed cover

Updated on 27 October 2026. Covers xSpeed Cache 1.4.4, released 19 October 2026.

Connecting your WordPress site to an AI assistant takes about two minutes, and the route is simple: connect your site to xSpeed Hub, then give Claude or ChatGPT one MCP connection at the Hub. From that moment your assistant can benchmark the site, tune cache settings, warm the cache, and re-test, talking back and forth with it until the numbers move. On our demo site, that loop took the PageSpeed score from 62 to 100, with cache hits landing in the 5–15 ms range.

The best part: the same single connection covers every site you add later. Attach a second, fifth, or fiftieth site to your Hub account and your AI reaches them all, nothing new to paste into any client.

TL;DR: pick your route

If you wantDo thisWhy
One AI connection that reaches every site you ownConnect each site to xSpeed Hub, then give your assistant a single MCP connection at the HubSites you add later are reachable through that same connection, with nothing new to paste
The shortest setup inside WordPressConnect Hub → sign in → approve from the xSpeed Cache top barNo token is copied anywhere: the site and the Hub exchange credentials behind the approval click
A fleet view, monitoring and rolesUse the Hub rather than per-site connectionsThe Hub adds a dashboard, daily monitoring, teams, and scoped credentials: read-only, per-site, per-tool
No hosted account at allPoint your AI straight at one site’s own MCP URLStill free, but it covers that one site, and every extra site means another connection in every client
The edge as well as the page cacheAdd the Cloudflare Enterprise add-on, shipped in Free 1.4.1 on 8 October 2026Whole pages are served from a location near the visitor, and your assistant can purge them

Why this works: your site becomes the tool, not the topic

Ask a chatbot “why is my WordPress site slow?” and you get generic advice, it cannot see your site. MCP, the Model Context Protocol, changes the relationship: instead of talking about your site, the AI gets typed tools to act on it: run_benchmark, get_cache_status, update_settings, purge_cache, start_preloader, and the rest.

Think of it as the difference between a consultant who mails you a PDF and one who is allowed to sit at the keyboard. The loop that gets a site to 100: measure, change one thing, measure again: is exactly the loop an AI can run tirelessly, and xSpeed Cache exposes every control it needs. Every WP-CLI command the plugin has is also available as an MCP tool, so nothing is out of reach.

xSpeed Hub sits above your sites as the broker: your AI holds one credential, and the Hub routes each tool call to the right site’s own MCP endpoint. That is why one connection scales from one site to a hundred.

The agent-first flow on xspeedcache.com: install, connect over MCP, ask for a perfect score

Nothing works until you opt in. A fresh install exposes no MCP access at all, and a Hub connection only ever has the scope you gave it.

Before you start

  • xSpeed Cache (free, wordpress.org/plugins/xspeed) installed and active. Run the setup wizard first so caching itself is healthy, the wizard even offers the Hub connection as a step.
  • Administrator access to the site.
  • An AI client that supports remote MCP servers. Claude (claude.ai, Claude Desktop, or the Claude Code CLI), ChatGPT with MCP connectors, or Cursor.

Step 1. Connect your site to xSpeed Hub

  1. In WordPress, click Connect Hub in the xSpeed Cache top bar (or open AI & agents → MCP Server → xSpeed Hub tab).
  2. Click Connect via xspeedcache.com. You are sent to the Hub carrying your admin email, so account creation is one click for new users.
  3. Sign in. Google or an emailed magic link, and approve the attachment.
  4. You land back on your site, connected. The site now appears in your Hub dashboard at app.xspeedcache.com.

No token is copied anywhere in this flow; the site and the Hub exchange credentials behind the approval click. Repeat these four clicks on each additional site. That is the only per-site work in this whole guide.

Step 2. Connect Claude or ChatGPT to the Hub

Now give your AI its one connection:

  1. In the Hub, open Connect.
  2. Choose the scope. The one-click default is full access; or restrict it: read-only, limited to chosen sites, or with specific tools denied. (You can tighten a live connection later without reconnecting.)
  3. Paste the generated config into your AI client: a one-liner for the Claude Code CLI, or an mcpServers JSON block for Claude Desktop, ChatGPT, or Cursor.

That’s the last copy-paste you’ll do. Sites added later are reachable through this same connection automatically. Step-by-step setup for each client, including ChatGPT, is in AI agents.

Step 3. Ask for the score

With the connection live, the workflow is a conversation:

You: Get my portfolio site to 100 on PageSpeed.

Claude: run_benchmark → score 62, LCP 4.1 s. Enabling minification, delaying three third-party scripts, turning on browser caching… start_preloader → warmed 48 URLs… run_benchmark → score 100, LCP 0.9 s. Done. I purged stale pages and left notes in the activity log.

Because the Hub knows all your sites, fleet questions work too: “Which of my sites has the worst hit ratio this week?”, “Purge the cache on the client shop”, “Compare last month’s PageSpeed runs on the blog.” The AI reads real numbers from your sites: stored PageSpeed Insights and GTmetrix history included: so its changes are grounded, and it re-tests after each one. Ready-made prompts for the score loop are in Raise PageSpeed with Claude.

xSpeed Hub release notes and the Hub explainer on the changelog page

What the Hub route gives you beyond the connection

  • Fleet dashboard: every site ranked worst-first, with health chips and drill-downs.
  • Daily monitoring, snapshots with Slack and email alerts when something regresses.
  • Teams: invite people as Owner, Admin, or Viewer; roles are enforced everywhere, including the AI surface, so a Viewer’s credential can never write.
  • Scoped connections: per-site access levels and denied tools; rotation preserves scope, and restrictions only ever narrow access.
  • Report history. PageSpeed Insights and GTmetrix runs per site, any two comparable side by side.

Alternative: connect directly to one site (no account)

Don’t want a hosted account? Every xSpeed Cache install speaks MCP at its own URL, and the direct route is still free:

  1. Open xSpeed Cache → AI & agents → MCP Server, choose the access level, and click Connect.
  2. Copy the generated snippet. Bearer-header config for any client, or just give an OAuth-capable client the bare endpoint (https://yoursite.com/xspeed/mcp) and approve the consent screen as an administrator.

The trade-off: the connection covers that one site only, and each additional site means another connection in every AI client. Full details in the MCP server setup guide.

How to verify it worked

  1. Easiest: ask the assistant to call get_cache_status (add “on ” if you have several). A real connection returns live cache stats; a broken one errors.
  2. In the browser: open your site logged out and check the response headers in DevTools (or curl -I yoursite.com). You want x-cache: HIT on the second load: a page served in the 5–15 ms class, before PHP even starts.
  3. The number that matters: hit ratio. Ask “what’s my hit ratio?” or check the Hub’s site drill-down. Healthy sites sit above 80%; below 50%, ask the AI why. The answer is usually an over-broad exclusion or a too-short cache lifetime.
  4. Trust but verify: the Hub’s Activity log records every tool call per account: what ran, on which site, by which connection, and whether it changed anything. (Each site also keeps its own AI activity log under AI & agents.)
  5. A second opinion from outside: run the page through xSpeed Scan before and after, and compare the delivery score. It probes the response from outside your network, so it reports what a visitor gets rather than what the dashboard believes.

Who doesn’t need this

If you run one small brochure site, never look at PageSpeed, and the setup wizard already got you a green score. You can stop at “install the plugin.” The agent workflow earns its keep when you tune regularly, run many sites, or want performance handled conversationally instead of through panels.

Guardrails and maintenance

  • Start read-only if you are unsure. Write tools are refused with a clear message, and you can widen the scope later without re-pasting anything.
  • Rotate on suspicion. If a credential may have leaked, rotate it. A fresh secret is minted and the old one dies instantly. Rotation always preserves the connection’s scope; it never widens access.
  • Brute force is handled: failed authentications are rate-limited per IP.
  • Monthly habit: skim the activity log, and remove connections you no longer use.

Cloudflare Enterprise shipped, and your agent can purge it

Cloudflare Enterprise is no longer on the roadmap. It landed in xSpeed Cache Free 1.4.1 on 8 October 2026, and that release’s changelog entry on wordpress.org (read 27 October 2026) is entirely the add-on: setup in four steps (Setup, Verify, Connect, Done), a card for each DNS record with a Copy button beside every value, and the add-on’s own page inside the dashboard instead of the store.

It is an add-on rather than a plan tier, and the Cloudflare Enterprise page states the terms (read 27 October 2026):

ItemWhat it costs
Cloudflare Enterprise add-on$5 per domain, per month
xSpeed Cache Pro licenceRequired, any paid plan: Yearly or Lifetime
A Cloudflare accountNot needed
A Cloudflare billNone
A second pluginNone

Whole pages are cached at the edge, not only images and scripts, and publishing a post clears those pages on Cloudflare as well as on your own server. Tiered Cache, where one Cloudflare location asks another before it asks your server, is always on, and so are HTTP/3 and Brotli. The managed firewall, rate limiting at 200 requests a minute per address, AI crawler blocking and the SSL certificate are included. Cart, checkout, account and logged-in pages are never stored at Cloudflare, the same exclusions the page cache already honours. Your nameservers stay where they are: you add two DNS records and point the website record at Cloudflare, and the plugin checks each one.

What the edge changes, measured rather than claimed: xSpeed Scan probed 1,748 WordPress sites between 30 August and 28 September 2026 and compared the ones whose edge answers with the ones that have no CDN.

MeasureNo CDNEdge serves the page
Median time to first byte415 ms, 1,163 sites117.5 ms, 226 sites
Pages answered in under 200 ms36.4%84.5%
xSpeed Scan delivery score, out of 1006792
Phones waiting over 2.5 s for LCP70.4%41.7%

Real-user LCP in the last row comes from Chrome UX Report data, which covers a smaller slice of that sample than the server probes do.

For the workflow this guide is about, the split between what the assistant may do and what you do is deliberate, and the add-on page says it plainly: “Your agent can purge on its own. Enabling, removing or re-pointing a domain stays with you.” Purging is a tool call; adding a domain is a decision with a bill behind it. The same controls answer on the command line as wp xspeed cfe status, enable, purge and verify, which means they are MCP tools too.

Cloudflare Enterprise reached xCloud before it reached the plugin. xCloud is managed hosting and server management for WordPress, Laravel, Node.js and Docker, from the same team, and it is the route to take when the hosting and the edge should come from one panel. Inside WordPress, the add-on is now the shorter path. The changelog carries every release.

Frequently Asked Questions

My AI says it cannot see one of my sites.

Check two things in the Hub: the site is attached (it appears on the dashboard), and the connection’s scope includes it, a site set to No access answers exactly like a site that does not exist.

Every call I make returns 401 Unauthorized.

The connection config in your AI client is stale or wrong. Open the Hub’s Connect panel, confirm the connection exists, and re-copy the config. For a direct site connection, check AI & agents → MCP Server on the site itself.

My write action was refused with a read-only message.

The connection is read-only, or that site is set to Read-only in the per-site levels. Edit the connection’s scope in the Hub. The change lands on the AI’s next call, no reconnect needed.

My calls suddenly started returning 429.

That IP hit the failed-authentication lockout. Fix the credential in the client and wait out the window; one successful login clears it.

My site’s direct MCP URL doesn’t respond.

Use the fallback endpoint https://yoursite.com/wp-json/xspeed/v1/mcp. It works even on plain permalinks. If the pretty URL 404s, re-save your permalinks under Settings → Permalinks.

Does this cost anything?

No. The MCP server ships in the free plugin, and an xSpeed Hub account is free. xSpeed Cache Pro adds Critical CSS, image conversion, RUM, and AI recommendations. All of which also become tools your assistant can drive.

Do I need the Hub, or will the plugin on its own do?

Both work. The plugin alone speaks MCP at its own URL and costs nothing. The Hub exists so that one credential reaches a fleet, and so that monitoring, roles and scoped access live in one place. One site and one client: take either. Two sites or two people: the Hub saves you a connection per site, per client.

Which version do I need for the Cloudflare Enterprise add-on?

The four-step setup arrived in xSpeed Cache Free 1.4.1 on 8 October 2026, and the current release is 1.4.4, last updated 19 October 2026 on wordpress.org. The add-on also needs an xSpeed Cache Pro licence on any paid plan and has its own licence key. On a Pro older than 1.3.0 the Network page keeps the card and asks a licensed Pro to update.

Can I let my assistant purge the edge without letting it touch my domain?

That is the default, and it is not a scope you have to configure. Purging is exposed to an agent; enabling, removing or re-pointing a domain stays a human action in the dashboard. The connection’s own scope still applies on top, so a read-only credential cannot purge either.

Can I stop one person on my team from writing through the AI?

Yes. Invite them as Viewer in the Hub. Roles are enforced on the AI surface as well as in the dashboard, so a Viewer’s credential is refused on every write tool rather than quietly ignored.

Go deeper:

Make your site load in milliseconds.

One switch. Zero bloat. Always free to start.