Ai Agent With MCP

🚀 AI Agent Using MCP Protocol

This project implements an artificial intelligence agent that interacts with external resources using the Model Context Protocol (MCP).

🚀 Quick Start

✨ Features

• The project enables interaction with external resources via the MCP.
• It provides access to user and message resources.
• It includes an MCP client and supports direct REST API access.

📦 Installation

Please ensure that you have installed Cursor on your system and configured npm.

Option 1: Installation via Terminal

Execute the following commands in the terminal:

# Install dependencies
npm install

# Compile the project
npm run build

# Start the server
npm start

# Run in development mode
npm run dev

💻 Usage Examples

Basic Usage

The project includes an MCP client that can be used to access available resources:

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

async function main() {
  const client = new Client({
    name: "hello-mcp-client",
    version: "1.0.0"
  });
  const transport = new StdioClientTransport({
    command: "node",
    args: ["build/index.js"]
  });
  
  try {
    await client.connect(transport);
    
    // List available resources
    const resources = await client.listResources();
    console.log("Available resources:", resources);
    
    // Read the content of the user resource
    const content = await client.readResource({ uri: "api://users" });
    console.log("\nUser list:", content);
  } catch (error) {
    console.error("Error executing the client:", error);
  }
}

main().catch(console.error);

Advanced Usage

You can also access resources through direct REST API:

# List all users
curl http://3.238.149.189:8080/users

📚 Documentation

Available Resources

The MCP server provides the following resources:

User Resources

• api://users: Lists all registered users in the system.
  • Returned information includes ID, name, phone number, and thread ID.
  • Format: JSON
  • Response example:

    {
      "content": [
        {
          "id": 1,
          "phoneNumber": "553496341404",
          "name": "Moisés Paschoalick",
          "threadId": "thread_bZEPVYVBvHxY9Ok6WqR63M2D"
        },
        {
          "id": 2,
          "phoneNumber": "553496338888",
          "name": "José Silva",
          "threadId": "1thread_t8SFjKio6yN9pppqypilwGoR__"
        },
        {
          "id": 3,
          "phoneNumber": "553496338889",
          "name": "Maria Antonia",
          "threadId": "1thread_t8SFjKio6yN9pppqypilwGoR__"
        }
      ],
      "pageable": {
        "pageNumber": 0,
        "pageSize": 12,
        "sort": {
          "empty": false,
          "sorted": true,
          "unsorted": false
        },
        "offset": 0,
        "paged": true,
        "unpaged": false
      },
      "last": true,
      "totalPages": 1,
      "totalElements": 3,
      "first": true,
      "size": 12,
      "number": 0,
      "sort": {
        "empty": false,
        "sorted": true,
        "unsorted": false
      },
      "numberOfElements": 3,
      "empty": false
    }
    

Message Resources

• hello://world: Returns a simple greeting message.
  • Format: Plain text (text/plain)
  • Response example: "Hello, World! This is my first MCP resource."

🔧 Technical Details

Prerequisites

• Node.js (a version compatible with AbortController)
• TypeScript
• @modelcontextprotocol/sdk