Chatbot MCP
@AndersonHqds
A simple client and server mcp
Overview
What is Chatbot MCP?
Chatbot MCP is an intelligent chatbot that uses the Model Context Protocol (MCP) to process natural language requests and perform operations such as CPF validation and recharge (add/subtract balance). It is built with TypeScript, Express.js, and OpenAI GPT-4, and is intended for developers who need a conversational interface for account management tasks.
How to use Chatbot MCP?
Install Node.js 18+, clone the repository, run npm install, and create a .env file with your OPENAI_API_KEY. Start the server with npx ts-node server.ts and the client with npx ts-node index.ts in a separate terminal. Then send natural language commands like “Realizar uma recarga de R$50 para o CPF 123.456.789-09” to perform recharge or debit operations.
Key features of Chatbot MCP
- Natural language processing using GPT-4
- Robust CPF validation (formatting, length, check digits)
- Recharge system with add and subtract operations
- Command-line interface for interaction
- REST API with MCP support
Use cases of Chatbot MCP
- Validate CPF numbers and perform balance recharge or debit
- Process natural language requests for account management
- Integrate an MCP-based chatbot into existing Node.js applications
FAQ from Chatbot MCP
What are the prerequisites for Chatbot MCP?
Node.js version 18 or higher, npm or yarn, and an OpenAI API key are required.
How do I run Chatbot MCP?
Start the server with npx ts-node server.ts and the client with npx ts-node index.ts in separate terminals.
What commands does Chatbot MCP support?
It supports natural language commands for recharge (e.g., “Realizar uma recarga de R$50 para o CPF 123.456.789-09”) and debit (e.g., “Realize um débito de x valor para o cpf y”).
How does CPF validation work?
The system accepts CPF with or without formatting (e.g., 123.456.789-09 or 12345678909), checks for exactly 11 digits, validates the check digits, and rejects CPFs with all identical digits.
What technologies does Chatbot MCP use?
It uses TypeScript, Express.js, OpenAI GPT-4, the Model Context Protocol (MCP), Zod for validation, and CORS for security.