ai-native-camp avatar

Day2 Supplement Mcp

This is a structured MCP learning module that walks you through Claude's Model Context Protocol in five blocks, from basic concepts to installing popular servers. It's built with strict two-phase pacing: first you get the explanation and hands-on exercise, then after you report back, it quizzes you before moving on. The protocol explicitly forbids rushing through both phases in one turn, which keeps you from passively reading without actually trying things. Starts by installing the latest curriculum with npx, lets you jump to any block, and includes bonus content on combining MCP with plugins. If you've been confused about what MCP actually is or how to connect external tools to Claude Code, this gives you a methodical walkthrough with enforced practice.

skills.sh installs
1.6K
GitHub stars
242
last updated
Aug 21, 2026

Install

$ npx -y skills add ai-native-camp/camp-1 --skill day2-supplement-mcp --agent claude-code

Installs into .claude/skills of the current project.

Files

Day 2 보충: MCP 딥다이브

이 스킬이 호출되면 아래 STOP PROTOCOL을 반드시 따른다.


STOP PROTOCOL — 절대 위반 금지

이 프로토콜은 이 스킬의 최우선 규칙이다. 아래 규칙을 위반하면 수업이 망가진다.

각 블록은 반드시 2턴에 걸쳐 진행한다

┌─ Phase A (첫 번째 턴) ──────────────────────────────┐
│ 1. references/에서 해당 블록 파일의 EXPLAIN 섹션을 읽는다    │
│ 2. 기능을 설명한다                                        │
│ 3. references/에서 해당 블록 파일의 EXECUTE 섹션을 읽는다    │
│ 4. "지금 직접 실행해보세요"라고 안내한다                     │
│ 5. ⛔ 여기서 반드시 STOP. 턴을 종료한다.                    │
│                                                          │
│ ❌ 절대 하지 않는 것: 퀴즈 출제, QUIZ 섹션 읽기             │
│ ❌ 절대 하지 않는 것: AskUserQuestion 호출                  │
│ ❌ 절대 하지 않는 것: "실행해봤나요?" 질문                   │
└──────────────────────────────────────────────────────────┘

  ⬇️ 사용자가 돌아와서 "했어", "완료", "다음" 등을 입력한다

┌─ Phase B (두 번째 턴) ──────────────────────────────┐
│ 1. references/에서 해당 블록 파일의 QUIZ 섹션을 읽는다       │
│ 2. AskUserQuestion으로 퀴즈를 출제한다                     │
│ 3. 정답/오답 피드백을 준다                                 │
│ 4. 다음 블록으로 이동할지 AskUserQuestion으로 묻는다         │
│ 5. ⛔ 다음 블록을 시작하면 다시 Phase A부터.                │
└──────────────────────────────────────────────────────────┘

Sponsors

Details

Repository
github.com/ai-native-camp/camp-1
Category
AI & Agent Building

More from ai-native-camp/camp-1

All 7
1mapbox avatarmapbox-mcp-devkit-patternsmapbox/mapbox-agent-skillsIntegration patterns for Mapbox MCP DevKit Server in AI coding assistants. Covers setup, style management, token management, validation workflows, and documenta1.6Kskills.sh installs
2ai-native-camp avatarday2-mcp-and-context-syncai-native-camp/camp-2AI Native Camp Day 2 MCP & Context Sync. MCP를 배우고 나만의 Context Sync 스킬을 만든다. "2일차", "Day 2", "MCP", "context sync" 요청에 사용.1.5Kskills.sh installs
3qodex-ai avatarfinancial-analysis-agentqodex-ai/ai-agent-skillsCreate agents for financial analysis, investment research, and portfolio management. Covers financial data processing, risk analysis, and recommendation generat1.3Kskills.sh installs
4orchestra-research avatartensorrt-llmorchestra-research/ai-research-skillsOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 1.1Kskills.sh installs
5dbt-labs avatarconfiguring-dbt-mcp-serverdbt-labs/dbt-agent-skillsGenerates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt. Use when setting up, configuring, or troubles1.1Kskills.sh installs
6orchestra-research avatardistributed-llm-pretraining-torchtitanorchestra-research/ai-research-skillsProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or cu1Kskills.sh installs