Frontapp MCP

🚀 Frontapp MCP Server

A Model Context Protocol (MCP) server for integrating Large Language Models (LLMs) with the Frontapp customer communication platform. This server allows you to monitor and control chats in real-time via a text interface or Webhooks, while providing comprehensive analytics capabilities.

✨ Features

• Real-time Conversation Monitoring: Receive all conversation updates in real-time via a text interface or Webhooks.
• Automation Rules: Automatically pause, modify, or mark conversations based on preset conditions.
• Data Collection: Obtain detailed conversation metadata for subsequent analysis.
• Scalability: Support large teams and high-traffic workspaces.

🛠️ Compatibility

• Compatible with all versions of Frontapp.
• Suitable for any integrated LLM, including GPT-4, Claude, PaLM, etc.

📦 Installation

Quick Installation

1. Clone the repository:

git clone git@github.com:yourusername/frontapp-mcp.git
cd frontapp-mcp

2. Install dependencies:

npm install

3. Configure environment variables and run:

cp .env.example .env
# Fill in your Frontapp API key and other configurations
npm run dev

📚 Documentation

For the full API documentation and development guide, please refer to the Official Documentation.

💻 Usage Examples

Basic Usage

1. Initialize the MCP Server

• Create a new workspace and enable MCP integration in Frontapp.
• Configure environment variables, including:
  • FRONTAPP_API_KEY: Your Frontapp API key.
  • PORT: The port the server listens on (default is 3000).
  • Other custom settings.

2. Connect to an LLM

• Use any compatible LLM service provider, such as:
  • OpenAI
  • Anthropic (Claude)
  • Google (PaLM)

3. Configure Webhooks

Define your custom logic in webhooks.json:

{
  "Rule ID": {
    "trigger": "event.type === 'message'",
    "action": "callWebhook('https://your-webhook-url')"
  }
}

Advanced Usage

Client Example

const mcp = new MCPClient('http://localhost:3000');

mcp.onMessage((message, context) => {
  console.log(`New message: ${message.text}`);
});

mcp.start();

Webhook Handler Example

export async function processWebhook(event) {
  if (event.type === 'new_message') {
    // Add custom logic here
    await mcp.call('logMessage', { message: event.message });
  }
}

🛠️ Development

Quick Development Commands

# Start the development server (supports hot reloading)
npm run dev

# Run tests
npm test

# Format code
npm run lint
npm run format

⚠️ Security Considerations

• Always use HTTPS for communication.
• Regularly update dependency libraries to prevent security vulnerabilities.
• Configure appropriate rate limits and authentication mechanisms.
• Encrypt sensitive data during storage and transmission.

📄 License

This project is licensed under the MIT License. For details, please refer to the LICENSE file.

🤝 Contribution

All contributions are welcome! For detailed information on how to contribute to this project, please refer to the Development Guide.

Important Links

• Official Documentation
• Frontapp Developer Documentation
• Model Context Protocol Specification