Mcpheonix

🚀 MCPheonix

MCPheonix is a simplified version of a Model Context Protocol (MCP) server implemented using Elixir's Phoenix framework. It enables AI models to interact with application data and functionality through a unified interface.

🚀 Quick Start

Prerequisites

• Elixir 1.14 or higher
• Erlang 25 or higher
• Phoenix 1.7.0 or higher
• Python 3.9+ (for Flux and Dart integration)
• Node.js 18+ (for Dart MCP server)
• Cloudflare account (for Durable Objects integration)

Installation

1. Clone the repository:

git clone https://github.com/yourusername/mcpheonix.git
cd mcpheonix

2. Install dependencies:

mix deps.get

3. Configure Cloudflare integration:

   • Create a Cloudflare Worker using the template in cloudflare/durable-objects-worker.js.
   • Deploy it to your Cloudflare account.
   • Set the following environment variables:
     • CLOUDFLARE_WORKER_URL: The URL of your deployed worker.
     • CLOUDFLARE_ACCOUNT_ID: Your Cloudflare account ID.
     • CLOUDFLARE_API_TOKEN: An API token with Workers and DO permissions.

4. Configure Flux integration (if using image generation):

   • Set up the Flux CLI environment as described in the Flux Integration section.

5. Configure Dart integration (if using task management):

   • Set up the Dart MCP server as described in the Dart Integration section.

6. Start the server:

mix phx.server

The server will be available at http://localhost:4001.

Adding a Custom MCP Server

MCPheonix is designed to work with multiple MCP servers. This system includes a flexible architecture for integrating custom MCP servers in the following ways:

1. Simple JSON Configuration: Define your server settings in priv/config/mcp_servers.json:

{
  "mcpServers": {
    "your_server_id": {
      "command": "/path/to/executable",
      "args": ["arg1", "arg2"],
      "env": {
        "ENV_VAR1": "value1",
        "ENV_VAR2": "value2"
      },
      "tools": {
        "your_tool": {
          "description": "Tool description",
          "parameters": [
            { "name": "param1", "type": "string", "description": "Parameter description" }
          ]
        }
      }
    }
  }
}

2. Custom Server: Extend the MCPServer class as needed to support custom functionality.

For detailed implementation information, refer to the Custom MCP Server documentation.

✨ Features

• Real-time notification streams (Server-Sent Events)
• JSON-RPC endpoints for client requests
• Simple resource system
• Event publishing/subscription mechanism
• Basic tool invocation
• Flux image generation integration
• Dart task management integration
• Scalable MCP server architecture
• Self-healing distributed architecture via Cloudflare Durable Objects
• Edge computing capabilities via Cloudflare Workers

🔧 Technical Details

Self-healing Distributed Architecture

MCPheonix implements a complex self-healing system through integration with Cloudflare Durable Objects and Workers, building a distributed and resilient architecture that can withstand failures and ensure continuous operation.

Key Components

• Durable Objects: Stateful serverless components running on Cloudflare's global edge network, maintaining consistency even in the event of failures.
• Edge Distribution: Critical application states are replicated across the global network to ensure uninterrupted operation even in the event of regional failures.
• Automatic Recovery: If an instance becomes unavailable, the system automatically recreates it from the latest state in durable storage.
• Real-time Communication: WebSocket support enables instant recovery coordination and state synchronization.
• Event-driven Architecture: Components react to state changes through a publish/subscribe model, allowing the system to self-heal and adapt to failures.

For detailed implementation information, refer to the Cloudflare Integration documentation.

💻 Usage Examples

Built-in Features - Resources

[Here you can add more specific code examples or descriptions about the resources if there are any in the original context. Since the original "Resources" part is not detailed enough, we can't provide more content for now.]