MCP Client X

🚀 MCP Client Example ☀️

This project demonstrates a simple client-server implementation using the Model Context Protocol (MCP), a standard way to connect large language models with tools and data.

🚀 Quick Start

This example shows you how to:

• Create an MCP server with custom tools.
• Connect to the server via an MCP client.
• Invoke tools and get responses from the server.

🎥 Tutorial Video

Click on the image above to watch the tutorial on MCP implementation.

📁 Project Structure

.
├── pyproject.toml
├── README.md
├── src
│   ├── client
│   │   └── mcp_client.py      # MCP client implementation
│   └── server
│       └── example_server.py  # MCP server with tools
└── uv.lock

🔧 Server Implementation

The server exposes two tools:

1. calculate_bmi - A simple calculator for computing the Body Mass Index (BMI).
2. fetch_weather - An asynchronous tool to fetch weather data from an external API.

💻 Client Implementation

The client connects to the server via standard input/output, initializes a session, and invokes the server's tools.

📦 Installation

Prerequisites

• Python 3.9+
• uv (Python package manager)

Installation Steps

# Install dependencies
uv install -e .

Run the Example

1. Start the client (which will automatically start the server):

uv run src/client/mcp_client.py

💻 Usage Examples

Basic Usage

The client will perform the following operations:

1. Connect to the server.
2. List available tools.
3. Invoke the BMI calculator with sample data.
4. Invoke the weather tool with sample coordinates.

Example Responses

Available tools: meta=None nextCursor=None tools=[...]
BMI calculation result: 22.857142857142858
Weather data: {"current_weather":{"temperature":14.2,"windspeed":12.6, ...}}

🧐 Testing with MCP Inspector

(Access http://localhost:5173 after running the following command)

  ❯ mcp dev src/server/example_server.py
Starting the MCP Inspector...
The proxy server is listening on port 3000

🔍 The MCP Inspector has been started and is running at http://localhost:5173 🚀
New SSE connection
Query parameters: {
  transportType: 'stdio',
  command: 'uv',
  args: 'run --with mcp mcp run src/server/example_server.py',

📚 Resources

This project uses:

• Model Context Protocol Python SDK
• MCP Official Documentation

📄 License

This project is under the MIT License - see the LICENSE file for details.