Cold's MCP Server - Project Management System

A powerful MCP (Model Context Protocol) server deployed on Cloudflare Workers that provides project and task management capabilities. This server allows AI assistants to create, manage, and track projects with associated todos through a simple API.

🚀 Features

• Project Management: Create, list, update, and delete projects

• Task Management: Create, organize, and track todos with priorities and due dates

• Cloud-Powered: Built on Cloudflare Workers for global availability

• Persistent Storage: Uses Cloudflare KV for reliable data persistence

• Real-time Sync: Server-Sent Events (SSE) support for real-time updates

• Type-Safe: Full TypeScript implementation with Zod validation

📋 Available Tools

Project Management

• create-project - Create new projects with name and description

• list-projects - List all projects with details

• update-project - Update project name or description

• delete-project - Delete project and all associated todos

Todo Management

• create-todo - Create todos with title, priority, and due dates

• list-todos - List todos (all or by project)

• update-todo-status - Update todo status (pending/in-progress/completed)

• update-todo-priority - Update todo priority (low/medium/high)

• update-todo-title - Update todo title

• delete-todo - Delete specific todos

Advanced Filtering

• list-todos-by-status - Filter todos by status

• list-todos-by-priority - Filter todos by priority

• list-todos-by-project-and-status - Filter by project and status

• list-todos-by-project-and-priority - Filter by project and priority

🛠️ Installation & Deployment

Quick Deploy

Local Development

# Clone and setup
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
cd my-mcp-server
npm install

# Start development server
npm run dev

# Deploy to production
npm run deploy

🔧 Configuration

The server uses Cloudflare KV namespaces for data storage:

• PROJECTS_KV - Stores project data

• TODOS_KV - Stores todo/task data

Update your wrangler.jsonc:

{
  "kv_namespaces": [
    {
      "binding": "PROJECTS_KV",
      "id": "your-namespace-id",
      "remote": true
    },
    {
      "binding": "TODOS_KV", 
      "id": "your-namespace-id",
      "remote": true
    }
  ]
}

🔌 Connecting to MCP Clients

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "cold-project-manager": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://your-worker.your-subdomain.workers.dev/sse"
      ]
    }
  }
}

Cloudflare AI Playground

1. Visit https://playground.ai.cloudflare.com/

2. Enter your worker URL: https://your-worker.your-subdomain.workers.dev/sse

3. Start managing projects with AI!

📊 Usage Examples

Creating a Project

// Create a new React project
{
  "action": "create-project",
  "projectName": "my-react-app",
  "projectDescription": "Modern React application with TypeScript"
}

Managing Todos

// Add a high-priority todo
{
  "action": "create-todo",
  "projectId": "project-uuid",
  "todoTitle": "Set up CI/CD pipeline",
  "todoPriority": "high"
}

// Update todo status
{
  "action": "update-todo-status", 
  "todoId": "todo-uuid",
  "todoStatus": "in-progress"
}

🏗️ Architecture

┌─────────────────┐    ┌──────────────────┐    ┌─────────────────┐
│   MCP Client    │───▶│ Cloudflare Worker │───▶│   KV Storage    │
│ (Claude/Playground)│    │  (MCP Server)   │    │ (Projects/Todos)│
└─────────────────┘    └──────────────────┘    └─────────────────┘

🎯 Use Cases

• AI Project Assistants: Help developers manage their coding projects

• Task Automation: Create and track development workflows

• Team Collaboration: Shared project management across teams

• Learning Projects: Organize tutorial and learning project progress

• Freelance Work: Manage client projects and deliverables

🤝 Contributing

1. Fork the repository

2. Create a feature branch

3. Add your tools to src/index.ts

4. Update storage schemas in src/storage.ts

5. Test with npm run dev

6. Deploy and submit a PR

📝 License

MIT License - feel free to use this in your own MCP servers!

🔗 Links

• Cloudflare Workers

• Model Context Protocol

• MCP SDK Documentation

• Cloudflare AI Playground