Claude에게 손발을 달아주는 마법,
외부 도구와 연결하기
The magic of giving Claude hands and feet,
connecting to external tools
기술 용어 없이, 일상 비유로 MCP를 이해해봅시다.
Let's understand MCP through everyday analogies, no jargon needed.
여러분의 스마트폰을 생각해보세요.
스마트폰 자체는 똑똑하지만, 앱을 설치하기 전에는 할 수 있는 게 한정되어 있습니다.
카카오톡을 설치하면 메시지를 보낼 수 있고, 카메라 앱이 있으면 사진을 찍을 수 있고, 은행 앱이 있으면 계좌를 확인할 수 있죠.
MCP 서버 = Claude에게 설치하는 앱입니다.
📱 스마트폰 = Claude (기본적으로 똑똑함)
📦 카카오톡 앱 = Slack MCP (메시지 보내기)
📦 깃허브 앱 = GitHub MCP (코드 관리)
📦 엑셀 앱 = PostgreSQL MCP (데이터 조회)
📦 파일 탐색기 = Filesystem MCP (파일 접근)
앱을 설치하듯이 MCP 서버를 추가하면, Claude가 할 수 있는 일이 확 늘어납니다.
Think of your smartphone.
The phone itself is smart, but before installing apps, what it can do is limited.
Install KakaoTalk to send messages, a camera app to take photos, a banking app to check accounts.
MCP servers = apps you install for Claude.
📱 Phone = Claude (smart by default)
📦 Messaging app = Slack MCP (send messages)
📦 GitHub app = GitHub MCP (manage code)
📦 Spreadsheet app = PostgreSQL MCP (query data)
📦 File manager = Filesystem MCP (access files)
Just like installing apps, adding MCP servers dramatically expands what Claude can do.
한 줄 요약: Claude에게 외부 세계와 소통하는 능력을 달아주는 표준 규격이다.
One-line summary: A standard protocol that gives Claude the ability to communicate with the outside world.
옛날에는 핸드폰마다 충전 단자가 달랐습니다. 삼성 따로, LG 따로, 애플 따로...
그런데 USB-C가 나오면서? 하나의 규격으로 모든 기기를 연결할 수 있게 됐죠.
MCP도 마찬가지입니다. 예전에는 Claude가 GitHub을 쓰려면 GitHub용 코드를, Slack을 쓰려면 Slack용 코드를 따로 만들어야 했습니다.
MCP라는 "USB-C 같은 표준"이 생기면서:
✅ GitHub MCP 서버 꽂으면 → GitHub 사용 가능
✅ Slack MCP 서버 꽂으면 → Slack 사용 가능
✅ DB MCP 서버 꽂으면 → DB 조회 가능
규격이 통일되어 있으니, 누구든 MCP 서버를 만들면 Claude에 바로 연결됩니다.
Remember when every phone had a different charger? Samsung, LG, Apple — all different...
Then USB-C came along and one standard connects all devices.
MCP is the same idea. Before, connecting Claude to GitHub needed GitHub-specific code, Slack needed Slack-specific code, etc.
Now with MCP as a "USB-C-like standard":
✅ Plug in GitHub MCP server → GitHub ready
✅ Plug in Slack MCP server → Slack ready
✅ Plug in DB MCP server → DB queries ready
Since the standard is unified, anyone can build an MCP server and it connects to Claude instantly.
MCP는 Model Context Protocol의 약자입니다. AI 모델이 외부 도구와 데이터에 접근하기 위한 개방형 표준 프로토콜이죠.
MCP stands for Model Context Protocol. It is an open standard protocol for AI models to access external tools and data.
USB처럼 하나의 규격으로 다양한 도구를 연결합니다. 각 도구마다 따로 연동 코드를 짤 필요 없이, MCP 서버만 있으면 바로 연결됩니다.
Like USB, a single standard connects diverse tools. No need to write separate integration code for each tool — just have an MCP server and you're connected.
GitHub, Slack, DB, 웹 검색, 파일 시스템 등 MCP 서버는 계속 늘어나고 있습니다. 직접 만들 수도 있어서 확장에 한계가 없습니다.
GitHub, Slack, DB, web search, filesystem — MCP servers keep growing. You can even build your own, so there's no limit to expansion.
MCP가 어떻게 Claude와 외부 도구를 연결하는지 흐름을 살펴봅니다.
Let's walk through how MCP connects Claude with external tools.
"GitHub 이슈 #42 확인하고 수정해줘"처럼 자연어로 요청합니다. Claude가 어떤 MCP 서버를 호출할지 자동으로 판단합니다.
You make a natural language request like "Check GitHub issue #42 and fix it." Claude automatically determines which MCP server to call.
Claude Code에 내장된 MCP Client가 JSON-RPC 2.0 형식으로 요청을 MCP Server에 전달합니다. 이 과정은 자동으로 이루어집니다.
The MCP Client built into Claude Code forwards the request to the MCP Server in JSON-RPC 2.0 format. This process happens automatically.
MCP Server가 실제 외부 API(GitHub API, DB 커넥션 등)를 호출하여 데이터를 가져옵니다.
The MCP Server calls the actual external API (GitHub API, DB connection, etc.) to fetch data.
외부 도구의 응답이 구조화된 형태로 Claude에게 돌아옵니다. Claude는 이 데이터를 분석하여 사용자에게 자연어로 답변합니다.
The external tool's response is returned to Claude in a structured format. Claude analyzes this data and answers the user in natural language.
가장 많이 사용되는 MCP 서버들입니다. 필요에 따라 골라서 연결하세요.
The most commonly used MCP servers. Pick and connect based on your needs.
| 서버명Server | npm 패키지npm Package | 주요 기능Key Features |
|---|---|---|
| Filesystem | @modelcontextprotocol/server-filesystem | 프로젝트 외부 파일 접근, 읽기/쓰기, 디렉토리 탐색Access files outside project, read/write, directory navigation |
| GitHub | @modelcontextprotocol/server-github | 이슈/PR 조회·생성, 코드 검색, 리포지토리 관리View/create issues & PRs, code search, repository management |
| Slack | @modelcontextprotocol/server-slack | 메시지 읽기/보내기, 채널 관리, 스레드 검색Read/send messages, channel management, thread search |
| PostgreSQL | @modelcontextprotocol/server-postgres | 데이터베이스 쿼리 실행, 스키마 조회, 테이블 분석Execute database queries, schema inspection, table analysis |
| Brave Search | @modelcontextprotocol/server-brave-search | 웹 검색, 최신 정보 조회, 뉴스 검색Web search, latest information lookup, news search |
| Memory | @modelcontextprotocol/server-memory | 대화 간 정보 저장, 장기 기억 관리, 지식 그래프Store info across conversations, long-term memory, knowledge graph |
MCP 서버를 Claude Code에 연결하는 두 가지 방법을 알아봅니다.
Learn two ways to connect an MCP server to Claude Code.
가장 간단한 방법입니다. 터미널에서 한 줄 명령어로 MCP 서버를 추가합니다.
The simplest method. Add an MCP server with a single command in the terminal.
설정 파일을 직접 수정하여 더 세밀한 제어가 가능합니다. 설정은 .claude/settings.json(프로젝트) 또는 ~/.claude/settings.json(전체)에 저장됩니다.
Edit the configuration file directly for finer control. Settings are stored in .claude/settings.json (project) or ~/.claude/settings.json (global).
Claude Code 대화 중에 /mcp 명령어로 연결 상태와 컨텍스트 비용을 바로 확인할 수 있습니다.
During a Claude Code session, use /mcp to instantly check connection status and context cost.
/mcp로 서버별 토큰 소비량을 확인하고, 자주 쓰지 않는 서버는 제거하는 것이 좋습니다./mcp and remove servers you rarely use.MCP 서버를 어디에 저장할지 결정합니다. 프로젝트 범위, 사용자 범위, 로컬 범위 세 가지가 있습니다.
Determines where to store the MCP server settings. There are three scopes: project, user, and local.
프로젝트 루트의 .claude/settings.json에 저장됩니다. Git에 커밋하여 팀 전체가 동일한 MCP 서버를 공유할 수 있습니다.
Stored in .claude/settings.json at the project root. Commit to Git so the whole team shares the same MCP servers.
~/.claude/settings.json에 저장됩니다. 내 컴퓨터의 모든 프로젝트에서 사용 가능하지만 나만 사용합니다.
Stored in ~/.claude/settings.json. Available across all projects on your machine, but only for you.
현재 프로젝트에서만, 나만 사용하는 설정입니다. 민감한 자격 증명이나 실험적인 서버 설정에 적합합니다.
Settings for the current project only, personal use only. Ideal for sensitive credentials or experimental server configurations.
서브에이전트(Subagent)를 사용할 때, 특정 에이전트에게만 특정 MCP 서버를 제공할 수 있습니다. 예를 들어, DB 분석 전담 에이전트에게만 PostgreSQL MCP를 부여하는 식입니다.
When using subagents, you can provide specific MCP servers to specific agents only. For example, giving only the DB analysis agent access to the PostgreSQL MCP.
MCP 서버를 연결하면 어떤 일이 가능해지는지, 3가지 실전 시나리오로 보여드립니다.
3 real-world scenarios showing what becomes possible when you connect MCP servers.
GitHub MCP 서버를 연결하면, 이슈 확인부터 PR 생성까지 한 번의 요청으로 자동화할 수 있습니다.
With the GitHub MCP server connected, you can automate everything from checking an issue to creating a PR in a single request.
Claude가 GitHub MCP를 통해 이슈 내용을 읽어옵니다.
Claude reads the issue content via GitHub MCP.
이슈와 관련된 코드를 찾아 수정합니다.
Finds and fixes the code related to the issue.
브랜치 생성, 커밋, PR 올리기까지 자동으로 처리합니다.
Automatically handles branch creation, commit, and PR creation.
PostgreSQL MCP 서버를 연결하면, DB 구조를 파악하고 마이그레이션 파일을 자동 생성할 수 있습니다.
With the PostgreSQL MCP server connected, you can understand the DB structure and auto-generate migration files.
PostgreSQL MCP를 통해 현재 DB 스키마를 읽어옵니다.
Reads the current DB schema via PostgreSQL MCP.
요청한 변경이 기존 데이터에 미치는 영향을 분석합니다.
Analyzes the impact of the requested change on existing data.
안전한 마이그레이션 SQL과 롤백 스크립트를 작성합니다.
Writes safe migration SQL and rollback scripts.
Slack MCP 서버를 연결하면, 채널의 메시지를 분석하여 요약 레포트를 자동 생성할 수 있습니다.
With the Slack MCP server connected, you can analyze channel messages and auto-generate summary reports.
Slack MCP를 통해 특정 채널의 최근 메시지를 가져옵니다.
Fetches recent messages from a specific channel via Slack MCP.
논의된 주제, 결정 사항, 액션 아이템을 자동으로 분류합니다.
Automatically categorizes discussion topics, decisions, and action items.
정리된 요약 레포트를 마크다운으로 생성합니다.
Generates a clean summary report in Markdown.
여러 MCP 서버를 동시에 연결하면, 서로 다른 서비스의 정보를 한 번에 조합할 수 있습니다. 기획자가 "이번 스프린트 진행 상황 정리해줘"라고 하면 끝!
Connect multiple MCP servers simultaneously to combine information across services. A PM just says "summarize this sprint's progress" and it's done!
MCP 서버를 사용할 때 반드시 알아야 할 사항들과 흔한 문제 해결법입니다.
Must-know information when using MCP servers, and solutions to common problems.
GITHUB_TOKEN, Slack MCP는 SLACK_BOT_TOKEN을 반드시 설정해야 합니다. 토큰 없이 연결하면 인증 에러가 발생합니다.GITHUB_TOKEN, Slack MCP requires SLACK_BOT_TOKEN. Connecting without a token will cause authentication errors.@modelcontextprotocol/server-* 형식이 올바른지 확인@modelcontextprotocol/server-* format/mcp를 입력하면 현재 연결된 MCP 서버의 상태와 서버별 컨텍스트 토큰 소비량을 즉시 확인할 수 있습니다. 각 MCP 서버는 도구 정의를 매 요청에 포함시키기 때문에, 서버가 많을수록 컨텍스트 비용이 증가합니다. 문제가 의심될 때 가장 먼저 실행해보세요./mcp to instantly check the status of connected MCP servers and token consumption per server. Since each MCP server includes tool definitions in every request, more servers means higher context cost. Run this first when you suspect an issue.MCP에 대해 가장 많이 궁금해하는 것들
The most common questions about MCP
/mcp를 입력하면 서버별 토큰 소비량을 확인할 수 있습니다. 실제 사용에서는 꼭 필요한 서버만 유지하는 것이 좋습니다./mcp in a Claude Code session to check token usage per server. In practice, keep only the servers you actually need.--scope project 플래그를 사용하거나 프로젝트 루트의 .claude/settings.json에 직접 작성하면, 해당 프로젝트를 사용하는 모든 팀원이 동일한 MCP 서버 설정을 공유할 수 있습니다. 다만 API 토큰 같은 민감한 정보는 환경변수로 분리하고, 각 팀원이 자신의 토큰을 로컬에 설정하는 것이 좋습니다. 설정 파일은 Git에 커밋하되, 토큰은 .env에 넣어 .gitignore로 관리하세요. 개인 전용 설정은 --scope user로 ~/.claude/settings.json에 저장하면 팀과 분리됩니다.--scope project flag or write directly to .claude/settings.json at the project root, and all teammates working on that project will share the same MCP server settings. Separate sensitive info like API tokens into environment variables, with each teammate setting their own token locally. Commit the config file to Git, but put tokens in .env and manage with .gitignore. Personal settings can be separated from the team using --scope user to save in ~/.claude/settings.json.백문이 불여일견! 지금 바로 따라해보세요. 가장 간단한 Filesystem MCP부터 시작합니다.
Seeing is believing! Follow along right now. We'll start with the simplest one: Filesystem MCP.
터미널을 열고 아래 명령어를 입력하세요. /path/to/allowed/dir 부분을 실제 폴더 경로로 바꿔주세요.
Open your terminal and type the command below. Replace /path/to/allowed/dir with your actual folder path.
서버가 잘 추가됐는지 확인합니다.
Check that the server was added successfully.
Claude Code를 실행하고 자연어로 요청해보세요!
Launch Claude Code and make requests in natural language!
MCP = Claude에게 외부 도구를 연결하는 표준 규격
설정법 = claude mcp add 한 줄이면 끝
범위 = project / user / local 로 팀/개인 분리
핵심 가치 = 자동화 + 실제 시스템과 상호작용
MCP = standard protocol for connecting Claude to external tools
Setup = just one line: claude mcp add
Scope = project / user / local to separate team/personal
Core value = automation + interact with real systems
시작이 어려우면, Filesystem MCP부터 연결해보세요:
claude mcp add filesystem npx -y @modelcontextprotocol/server-filesystem /path
If you're not sure where to start, try connecting the Filesystem MCP first:
claude mcp add filesystem npx -y @modelcontextprotocol/server-filesystem /path