convez.ai
PluginDesenvolvimento WebIntermediário
hadv

YiTam - Chat Bot Claude com MCP

hadv/yitam

Chat bot TypeScript com Claude AI e integração MCP

Ver no GitHub
InicialPluginScore · de 0 a 100

Aplicação de chat em TypeScript que integra a API Claude com Model Context Protocol (MCP) para capacidades aprimoradas de IA. Inclui servidor Node.js/Express e cliente React, pronto para deployment em Docker com suporte a domínios customizados e SSL.

Instalação

$npx convez-ai hadv/yitam

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
0
Acompanhando
1
Saúde
42%
Último commit
há 1 mês
Versão
v0.2.2
Issues abertas
6
Contribuidores
2

Casos de uso

  • Conversas alimentadas por IA com contexto protocolar
  • Deployment em produção com Docker e HTTPS
  • Integração de tools e skills via Model Context Protocol

Veredito

Stack sólido (Express + React + Claude) com infraestrutura de deployment bem documentada. A integração MCP adiciona extensibilidade, mas o README original vietnamita sugere contexto ainda não totalmente alinhado com escopo; útil para quem quer boilerplate production-ready de chat AI.

README

A tradução para o português deste README ainda está na fila.

TypeScript Claude Chat Bot with MCP Integration

A modern chat bot application built with TypeScript that uses Claude AI API to power conversations, with Model Context Protocol (MCP) integration for enhanced AI capabilities.

Components

  • Server: Node.js Express server that connects to Claude AI API using the Anthropic SDK
  • Client: React-based web application that provides a chat interface
  • MCP Integration: Model Context Protocol integration for enhanced AI tool capabilities

Prerequisites

  • Node.js (LTS version) - recommended to use nvm use --lts
  • npm - for package management
  • Docker and Docker Compose - for production deployment
  • Anthropic API key
  • MCP integration setup

Setup

Local Development

  1. Clone the repository
  2. Install dependencies:
    npm run install:all
    
  3. Configure environment variables:
    • Copy server/.env.example to server/.env
    • Add your Anthropic API key to server/.env
    • Configure MCP-related environment variables

Docker Production Deployment

  1. Clone the repository
  2. Configure environment variables:
    • Copy server/.env.example to server/.env
    • Add your Anthropic API key to server/.env
    • Configure MCP-related environment variables
  3. Build and run with Docker Compose:
    docker-compose up --build -d
    
  4. Access the application:

The application uses the unless-stopped restart policy, which means containers will automatically restart:

  • On failure/crash
  • When Docker daemon restarts
  • After system reboots But will respect manual stop commands, making maintenance easier.

Domain Configuration

When deploying with a custom domain (e.g., yitam.org), follow these important steps:

  1. SSL Certificates:

    • Create an ssl directory at the root of your project
    • Place your SSL certificates in the directory:
      • ssl/yitam.org.crt - Your SSL certificate
      • ssl/yitam.org.key - Your private key
    • Add the ssl directory to your .gitignore to avoid committing sensitive files
    • Use the provided get-ssl-cert.sh script to automatically obtain and configure SSL certificates with Let's Encrypt
  2. DNS Configuration:

    • Configure your domain's DNS records to point to your server's IP address
    • Both www.yitam.org and yitam.org are supported in the configuration
  3. Access the application:

The application is configured to automatically restart in case of crashes or system reboots.

To check container status:

docker-compose ps

To view logs:

docker-compose logs -f

To stop the application:

docker-compose down

Running the application

Development mode

To run both server and client in development mode:

npm run dev

Or separately:

npm run server  # Run just the server
npm run client  # Run just the client

Production mode

Using Docker (Recommended)

See Docker Production Deployment section above.

Manual Production Setup

To build for production:

npm run build

Then to run the server:

cd server && npm start

Server API

The server uses Socket.IO for real-time communication with the client, and integrates with the Model Context Protocol for enhanced AI tool capabilities.

Support the Project

If you find this project useful, please consider supporting its development:

Sponsor

Your support helps maintain and improve the project!

Technology Stack

  • Server:

    • TypeScript
    • Express
    • Socket.IO
    • Anthropic SDK (Claude AI)
    • Model Context Protocol (MCP) SDK
  • Client:

    • TypeScript
    • React 19
    • Socket.IO Client
    • React Markdown
    • Vite 6
  • Production Environment:

    • Docker
    • Docker Compose
    • Nginx (serving client and reverse proxy)
    • Let's Encrypt SSL certificate automation
Ver o original no GitHub

Bom para

Relacionados