My MCP Worker

🚀 Building an MCP Server with Cloudflare Workers

The Model Context Protocol (MCP) is an open standard that enables interaction between AI agents and services. By setting up an MCP server, you can allow AI assistants to directly access your API. The combination of Cloudflare Workers and the workers-mcp package provides a powerful and scalable solution for building an MCP server.

🚀 Quick Start

Step 1: Create a New Cloudflare Worker

First, initialize a new Cloudflare Worker project:

npx create-cloudflare@latest my-mcp-worker
cd my-mcp-worker

Then, authenticate your Cloudflare account using the following command:

wrangler login

Step 2: Configure Wrangler

Update your wrangler.toml file to include the correct account information:

name = "my-mcp-worker"
main = "src/index.ts"
compatibility_date = "2025-03-03"
account_id = "your-account-id"

📦 Installation Guide

Prerequisites

Before you start, make sure you have the following:

• A Cloudflare account
• Node.js installed
• Wrangler CLI installed (npm install -g wrangler)

Install MCP Tools

To enable MCP support, install the workers-mcp package:

npm install workers-mcp

Run the following command to set up:

npx workers-mcp setup

This will perform the following actions:

• Add necessary dependencies
• Set up a local proxy for testing
• Configure the Worker to comply with the MCP specification

💻 Usage Examples

Basic Usage

Update your src/index.ts file to define your MCP server:

import { WorkerEntrypoint } from 'cloudflare:workers';
import { ProxyToSelf } from 'workers-mcp';

export default class MyWorker extends WorkerEntrypoint<Env> {
  /**
   * A friendly greeting from your MCP server.
   * @param name {string} The user's name.
   * @return {string} A personalized greeting.
   */
  sayHello(name: string) {
    return `你好，来自一个 MCP 工作者，${name}！`;
  }

  /**
   * @ignore
   */
  async fetch(request: Request): Promise<Response> {
    return new ProxyToSelf(this).fetch(request);
  }
}

Key Components:

• WorkerEntrypoint: Manages incoming requests and method exposure.
• ProxyToSelf: Ensures MCP protocol compliance.
• sayHello method: An example MCP function that an AI assistant can call.

Advanced Usage

You can extend your MCP server by integrating external APIs. Here is an example of fetching weather data:

export default class WeatherWorker extends WorkerEntrypoint<Env> {
  /**
   * Get weather data for a specified location.
   * @param location {string} The city or postal code.
   * @return {object} Weather details.
   */
  async getWeather(location: string) {
    const response = await fetch(`https://api.weather.example/v1/${location}`);
    const data = await response.json();
    return {
      temperature: data.temp,
      conditions: data.conditions,
      forecast: data.forecast
    };
  }

  async fetch(request: Request): Promise<Response> {
    return new ProxyToSelf(this).fetch(request);
  }
}

Deployment

After writing your code, you can deploy your MCP server using the following command:

npm run dev

This will start a Worker in a development environment.

Testing

To test your MCP server, you can use the following command:

curl http://localhost:8787

Depending on the code you've written, you'll get the corresponding response.

Security Measures

To protect your MCP server, it is recommended to take the following security measures:

1. Configure appropriate CORS policies.
2. Use environment variables to store sensitive information.
3. Enable rate limiting to prevent abuse.

By following the above steps, you have successfully built an MCP server based on Cloudflare Workers, and you can integrate external APIs and perform basic tests.