deploy-docusaurus-mcp-cloudflare

Deploy to Cloudflare Workers

Done when

curl https://<your-domain>/mcp returns the status JSON with "initialized": true, a docCount above 0, and baseUrl on your production domain.

Before you start

• The plugin is set up: npm run build writes build/mcp/bundle.json. If not, follow Getting started first.
• A Cloudflare account.

How to use this guide

• Do the steps in order. Run them yourself, or walk the user through them one at a time if they'd rather do it themselves or you can't run them.
• After each step, run its check. Don't move on until it passes.
• If a check fails, look for the matching symptom under Troubleshooting. If none matches, stop and tell the user what you saw.
• A step marked Needs the user needs a person. Tell the user what to do and wait for them to confirm it's done.
• Ask the user before running a step marked Confirm first.
• Don't ask the user to paste passwords, tokens, or keys into the chat. When a step needs one, tell the user where to put it.

Steps

1. Add the Worker {#worker}

worker.js

import { createWebRequestHandler } from 'docusaurus-plugin-mcp-server/adapters';
import bundle from './build/mcp/bundle.json' with { type: 'json' };

const mcp = createWebRequestHandler({ artifacts: bundle });

export default {
  fetch(request, env) {
    if (new URL(request.url).pathname === '/mcp') {
      return mcp(request);
    }
    return env.ASSETS.fetch(request);
  },
};

The env.ASSETS.fetch fallback only runs if you add more paths to run_worker_first. The adapter entry point imports no Node.js built-ins, so you don't need the nodejs_compat flag.

Check: worker.js is next to docusaurus.config.js and imports ./build/mcp/bundle.json.

If the check fails: see Troubleshooting.

2. Add wrangler.jsonc {#wrangler}

wrangler.jsonc

{
  "name": "my-docs",
  "main": "worker.js",
  "compatibility_date": "2026-10-01",
  "assets": {
    "directory": "./build",
    "binding": "ASSETS",
    "not_found_handling": "404-page",
    "run_worker_first": ["/mcp"]
  }
}