Frontapp MCP Server
About
A Model Context Protocol server that integrates large language models with Frontapp's customer communication platform. It enables LLMs to access and manipulate Frontapp data—such as conversations, contacts, and tags—and automate workflows using natural language commands.
Details
- Author
- zqushair
- Downloads
- 207
- Categories
- Other
Jump to
- Conversation management (retrieve, create, update)
- Contact management (access and update contact data)
- Tag management (apply and remove tags)
- Inbox management (access inbox information)
- User management (retrieve user details)
- Real‑time webhook integration with secure authentication
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Frontapp MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via Smithery or manually by cloning the repository, installing dependencies, configuring a .env file with Frontapp API credentials, then building and starting the server. Use the provided TypeScript client library to call tools like getConversations and sendMessage through the MCP protocol.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"frontapp mcp server": {
"Frontapp-MCP": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@zqushair/frontapp-mcp",
"--client",
"claude"
]
}
}
}
}McpServers
{
"Frontapp-MCP": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@zqushair/frontapp-mcp",
"--client",
"claude"
]
}
}Frontapp MCP Server
A Model Context Protocol (MCP) server for integrating Large Language Models (LLMs) with Frontapp's customer communication platform.
📚 View Full Documentation in /docs
Overview
This project implements an MCP server that acts as a bridge between LLMs and Frontapp's API. It enables LLMs to access and manipulate Frontapp data (conversations, contacts, tags, etc.) and automate Frontapp workflows using natural language commands.
The server supports real-time updates and event-driven automation using webhooks from Frontapp.
Features
- Conversation Management: Retrieve, create, update, and manage conversations
- Contact Management: Access and update contact information
- Tag Management: Apply and remove tags from conversations
- Inbox Management: Access inbox information
- User Management: Retrieve user details
- Webhook Integration: Receive and process real-time events from Frontapp
- Secure Authentication: Verify webhook signatures and handle API authentication
- Secure Credential Storage: Store sensitive information with AES-256 encryption
- HTTPS Support: Secure communications with TLS/SSL encryption
Architecture
The MCP server follows a modular architecture:
1. API Gateway: Handles incoming requests from LLMs and webhooks from Frontapp
2. Request Handlers: Process requests from LLMs and interact with the Frontapp API
3. Webhook Handlers: Process webhooks from Frontapp and update LLM context
4. Frontapp API Client: Encapsulates the logic for interacting with the Frontapp API
5. Data Models: Define the structure of data exchanged between LLMs, the MCP server, and Frontapp
6. Configuration: Stores settings for the MCP server
Prerequisites
- Node.js (v16 or higher)
- npm or yarn
- Frontapp API credentials
- A publicly accessible URL for webhooks (for production use)
Installation
Installing via Smithery
To install frontapp-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @zqushair/frontapp-mcp --client claude
For detailed installation instructions, see the Installation Guide.
Quick start:
1. Clone the repository:
git clone https://github.com/zqushair/Frontapp-MCP.git
cd Frontapp-MCP
2. Install dependencies:
npm install
3. Create and configure the .env file:
cp .env.example .env
# Edit the .env file with your Frontapp API credentials
4. Build and start the project:
npm run build
npm start
Documentation
Comprehensive documentation is available in the /docs directory:
- 📖 Main Documentation - Overview and introduction
- 🔧 Installation Guide - Detailed setup instructions
- 📚 API Reference - Available tools and endpoints
- 🔔 Webhook Integration - Real-time event processing
- 🔒 Credential Storage Guide - Secure credential management
- 🔐 HTTPS Setup Guide - Secure communications setup
- 💻 Development Guide - Contributing to the project
Usage
API Usage
The Frontapp MCP integration exposes a set of tools that can be called by LLMs through the MCP protocol. For detailed information about the available tools and their parameters, see the API Reference.
Client Library
The project includes a TypeScript client library (src/frontapp-mcp-client.ts) that LLMs can use to interact with the MCP server:
import { FrontappMcpClient } from './frontapp-mcp-client.js';
// Create a client instance
const client = new FrontappMcpClient('http://localhost:3000');
// Get a list of conversations
const conversations = await client.getConversations({ status: 'open' });
// Send a message to a conversation
await client.sendMessage('cnv_123', 'Hello, how can I help you today?');
The client library provides:
- Type-safe methods for all available tools
- Error handling with custom error handlers
- Retry logic with exponential backoff
- Comprehensive TypeScript interfaces
A complete example of client usage is available in src/examples/client-usage-example.ts.
Webhook Integration
The integration supports receiving and processing webhooks from Frontapp for real-time event notifications. For detailed information about webhook integration, see the Webhook Integration Guide.
Development
For detailed development information, see the Development Guide.
Quick Development Commands
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
