Frontapp MCP
A Model Context Protocol server that integrates LLMs with Frontapp's customer communication platform, enabling access to conversations, contacts, and tags while supporting real-time updates via webhooks.
A Model Context Protocol server that integrates LLMs with Frontapp's customer communication platform, enabling access to conversations, contacts, and tags while supporting real-time updates via webhooks.
A Model Context Protocol (MCP) server for integrating Large Language Models (LLMs) with Frontapp's customer communication platform.
? View Full Documentation in /docs
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.
The MCP server follows a modular architecture:
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:
Clone the repository:
git clone https://github.com/zqushair/Frontapp-MCP.git
cd Frontapp-MCP
Install dependencies:
npm install
Create and configure the .env
file:
cp .env.example .env
# Edit the .env file with your Frontapp API credentials
Build and start the project:
npm run build
npm start
Comprehensive documentation is available in the /docs directory:
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.
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
.
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.
For detailed development information, see the Development Guide.
# Start development server with hot reloading
npm run dev
# Run tests
npm run test:api
npm run test:conversations
npm run test:tags
npm run test:contacts
npm run test:webhooks
# Lint and format code
npm run lint
npm run format
# Build for production
npm run build
# Check TypeScript types without compiling
npm run typecheck
The project includes a Dockerfile for containerized deployment. This multi-stage build process creates an optimized production image.
# Build the Docker image
docker build -t frontapp-mcp .
# Run the Docker container
docker run -p 3000:3000 --env-file .env frontapp-mcp
If you encounter TypeScript errors during the Docker build process, they need to be fixed before the build can succeed. Common issues include:
Always run npm run typecheck
or npm run build
locally before building the Docker image to catch and fix these issues early.
npm run generate-key
npm run generate-cert
This project is licensed under the MIT License - see the LICENSE file for details.
Contributions are welcome! Please see the Development Guide for information on how to contribute to the project.