이는 도구와 자원을 포함한 핵심 기능을 시연하는 모델 컨텍스트 프로토콜(MCP) 서버 구현의 기본 예시입니다.

설정 단계

1. 프로젝트 초기화 (로컬 폴더에 가서 PowerShell이나 cmd를 실행):

2. 가상 환경을 만들고 활성화하세요

3. 의존성 설치:

또는

특징

서버는 다음과 같은 기능을 구현합니다:

도구

• add(a: int, b: int): 두 개의 숫자를 더함
• subtract(a: int, b: int): 첫 번째에서 두 번째 숫자를 뺀다

자료

• greeting://{name}: 개인화된 인사말을 반환합니다

서버 운영

개발을 위해 MCP 인스펙터와 함께 서버를 실행하려면:

서버를 정상적으로 실행하려면:

Claude 데스크톱 앱에 서버를 설치하려면:

MCP VS 코드로 연결해

• vs 코드에서 폴더/mcp-server-basic을 열어

• 터미널을 열고 명령어를 실행합니다:

• Cntrl+Shift+I 버튼을 클릭하여 vs 코드에서 채팅을 시작하세요

• Github로 로그인하고 설정

• 아래 단계를 따라 (vs code 사용자 설정에 MCP 설정을 추가하는 두 가지 방법):

데모를 시청하세요

프로젝트 구조

• main.py: 도구 및 자원이 포함된 메인 서버 구현
• pyproject.toml: 프로젝트 구성 및 의존성

2.

MCP Server Basic Example

This is a basic example of a Model Context Protocol (MCP) server implementation that demonstrates core functionality including tools and resources.

Setup Steps

1. Initialize the project (Go to any local folder and launch powershell or cmd):

uv init mcp-server-basic
cd mcp-server-basic

2. Create virtual environment and activate it

  uv venv
  .venv\Scripts\activate

3. Install dependencies:

uv add "mcp[cli]"

or

uv add -r requirements.txt

Features

The server implements the following features:

Tools

• add(a: int, b: int): Adds two numbers
• subtract(a: int, b: int): Subtracts second number from first

Resources

• greeting://{name}: Returns a personalized greeting

Running the Server

To run the server with the MCP Inspector for development:

uv run mcp dev main.py

To run the server normally:

uv run mcp run

To install the server in Claude desktop app:

uv run mcp install main.py

MCP connect in VS code

• Open folder/mcp-server-basic in vs code
• open terminal and run below command :

uv run main.py

• Click Cntrl+Shift+I to launch chat in vs code
• Do login with Github and setup
• Folow the below steps (two way to add mcp configuration for vs code user settings):

Watch the demo

Project Structure

• main.py: Main server implementation with tools and resources
• pyproject.toml: Project configuration and dependencies

2.0 Agentic AI And GENERATIVE AI With MCP Bootcamp

Enroll Now

Course Overview:

Mentors: Sourangshu Paul, Mayank Aggarwal , Krish And Sunny

Start Date:May 10th 2025

Timing: 8am to 11am IST(Saturday And Sunday)

Duration : 4-5 months

This course is designed for AI developers, machine learning engineers, data scientists, and software engineers looking to build expertise in agentic AI, multi-agent systems, and AI-powered automation. Whether you are new to AI agents or have experience in NLP and GenAI, this course will equip you with the knowledge and hands-on skills required to develop, deploy, and manage AI agents at scale. By the end of the course, you will have a strong foundation in agentic AI frameworks, multi-agent collaboration, real-world automation, and end-to-end AI deployment, along with practical experience through real-world projects.