Model Context Protocol, 또는 MCP는 애플리케이션이 LLMs에 컨텍스트를 제공하는 방법을 표준화하는 개방형 프로토콜입니다. 다른 말에서는 LLM 기반 애플리케이션에 대한 통합 프레임 워크를 제공하여 데이터 소스에 연결하고 컨텍스트를 사용하며, 표준 프롬프트를 실행합니다.

MCP 생태계는 세 가지 특정 구성 요소를 개요 :

• MCP Servers 핸들: 도구 가용성 (기능이 사용할 수 있는지 제외), 도구 실행 (요구될 때 그 기능을 실행), 리소스로 정적 내용 (참고할 수 있는 데이터 제공), 미리 설정된 프롬프트 (일반적인 작업을 위한 표준 템플릿)

-Clients 관리: 서버 연결, LLM 통합, 컴포넌트 사이 전달 메시지

• Hosts 제공 : Frontend 인터페이스, MCP 기능 서핑, 전반적인 생태계의 통합 지점

이 건축은 다른 성분이 상호 운용성을 유지하면서 독립적으로 개발될 수 있는 모듈형 시스템을 만듭니다. 이 사용자는 다양한 지원 응용 프로그램을 통해 다른 LLM 관련 기능에 대한 MCP 서버를 만들 수 있습니다.

Standardizing LLM Interaction with MCP Servers

Model Context Protocol, or MCP, is an open protocol that standardizes how applications provide context to LLMs. In other words it provides a unified framework for LLM based applications to connect to connect to data sources, get context, use tools, and execute standard prompts.

The MCP ecosystem outlines three specific components:

• MCP Servers handle: tool availability (exposing what functions are available), tool execution (running those functions when requested), static content as resources (providing data that can be referenced), preset prompts (standardized templates for common tasks)

• Clients manage: Connections to servers, LLM integration, message passing between components

• Hosts provide: Frontend interfaces, surfacing of MCP functionality to users, integration points for the overall ecosystem

This architecture creates a modular system where different components can be developed independently while maintaining interoperability. This let’s users make MCP servers for different LLM related functionalities then plug and play across a variety of supported applications. Commonly used to integrate services APIs and tools, or connect to local datasources on your own machine.

MCP Server Components

MCP servers form the foundation of the protocol by exposing standardized capabilities through well-defined interfaces. Hosts and clients can then connect to these servers using the protocol standard, but how these capabilities are presented to users remains flexible and open to developers. That means that the actual implementation and user experience is entirely up to the developer - whether through command line interfaces, graphical applications, or embedded within larger systems.

In this guide, we’ll focus on building an example MCP server with core capabilities, along with a simple client implementation to demonstrate the interaction patterns. To start, let’s go over the main components of an MCP Server:

Tools

Tools are functions that the LLM can invoke to perform actions or retrieve information. Each tool is defined with:

{
  name: string;          // Unique identifier for the tool
  description?: string;  // Human-readable description
  inputSchema: {         // JSON Schema for the tool's parameters
    type: "object",
    properties: { ... }  // Tool-specific parameters
  }
}

Tools allow LLMs to interact with external systems, execute code, query databases, or perform calculations. They represent actions that have effects or compute new information.

Resources

Resources represent data sources that can be accessed by the client application. They are identified by URIs and can include:

{
  uri: string;           // Unique identifier for the resource
  name: string;          // Human-readable name