Cloudflare Workshop Server

A Model Context Protocol (MCP) server implementation for Cloudflare Workers that provides chess-related tools and functionality using the Chess.com API.

⚠️ README generated by AI

Context

This MCP server was developed for the Cloudflare Workshop on "Building and Deploying Remote MCP Servers with Cloudflare" 🔗 Workshop Link

Features

• Get daily chess puzzles from Chess.com
• View currently live chess streamers
• Retrieve detailed player information and statistics
• List titled players by category (GM, IM, etc.)
• Implements the Model Context Protocol for AI assistant integration

Claude Desktop Setup

To use this MCP server with Claude desktop application:

1. Open Claude desktop settings
2. Navigate to the configuration file location
3. Add the following configuration to enable the chess tools:

{
  "mcpServers": {
    "workshop_chess": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://cloudflare-workshop-mcp-server.donovan-5a5.workers.dev/sse"
      ]
    }
  }
}

Prerequisites

• Node.js (v18 or later recommended)
• npm (included with Node.js)
• Cloudflare account (for deployment)

Setup

1. Clone the repository:

2. Install dependencies:

   npm install
   

3. Set up environment variables: Create a .dev.vars file in the project root for local development with any required API keys or configuration values.

Local Development

To run the server locally:

npm run dev

This will start the development server using Wrangler, Cloudflare's command-line tool for Workers. The server will be available at http://localhost:8787 by default.

Available Scripts

• npm run dev or npm start: Start the development server
• npm run deploy: Deploy to Cloudflare Workers
• npm run format: Format code using Biome
• npm run lint:fix: Lint and fix code issues
• npm run type-check: Check TypeScript types

Deployment

To deploy the MCP server to Cloudflare Workers:

1. Make sure you're logged in to Cloudflare:

   npx wrangler login
   

2. Push environment variables to Cloudflare:

   npx wrangler secret bulk .dev.vars
   

3. Deploy the worker:

   npm run deploy
   

4. After deployment, your MCP server will be available at the URL provided in the deployment output.

Usage Examples

The MCP server provides several chess-related tools that can be used by AI assistants or other clients that implement the Model Context Protocol.

Example Prompts

Here are some example prompts you can use with an AI assistant that has access to this MCP server:

Get Today's Chess Puzzle

Can you show me today's chess puzzle from Chess.com?

Find Live Chess Streamers

Who is currently streaming chess live?

Get Player Information

Tell me about the chess player MagnusCarlsen.

Get Player Statistics

What are the chess ratings and statistics for Hikaru?

List Titled Players

Can you give me some GrandMasters FIDE ranking ?