Skip to main content
Glama

스웨거 익스플로러 MCP

Claude를 통해 Swagger/OpenAPI 사양을 탐색하고 분석하기 위한 MCP(Management Control Plane) 서버입니다.

빠른 시작

npx를 사용하여 전역적으로 설치하고 실행합니다.

지엑스피1

또는 환경 변수를 사용하여 설치합니다.

npx -y @johnneerdael/swagger-mcp \ --env BASE_URL=/api \ --env AUTH_TOKEN=your-token \ --env PORT=3000

Related MCP server: Swagger MCP

Claude Desktop 설치

  1. 클로드 데스크톱 열기

  2. 설정(기어 아이콘)을 클릭하세요

  3. "도구 및 통합"을 선택하세요

  4. "MCP 서버 추가"를 클릭하세요

  5. 다음을 입력하세요.

    Name: Swagger Explorer Command: npx -y @johnneerdael/swagger-mcp Arguments: --swagger-url=$SWAGGER_URL
  6. "설치"를 클릭하세요

Claude와 함께 사용

클로드와의 상호작용 사례는 다음과 같습니다.

기본 스웨거 탐색

Human: Can you explore the Swagger documentation at http://localhost:8080/docs? Claude: I'll help you explore that Swagger documentation using the Swagger Explorer MCP. Let me analyze the API endpoints and schemas for you: [Claude would then use the MCP to fetch and analyze the Swagger documentation]

특정 엔드포인트 분석

Human: What are the available response schemas for the /pets POST endpoint? Claude: I'll check the response schemas for that endpoint using the MCP. [Claude would use the MCP to fetch specific endpoint details]

스키마 분석

Human: Can you show me the detailed structure of the Pet schema? Claude: I'll retrieve the detailed schema information using the MCP. [Claude would use the MCP to analyze the schema structure]

특징

  1. 인증 지원

    • 베어러 토큰 인증

    • 환경 변수를 통해 구성 가능

  2. 사용자 정의 응답 형식

    • 최소 형식: null/빈 값 제거

    • 자세한 형식: 메타데이터 및 타임스탬프 포함

    • 원시 형식: 수정되지 않은 응답

  3. 스키마 분석

    • 자세한 부동산 탐색

    • 응답 스키마 분석

    • 스키마 관계

  4. API 탐색

    • 경로 목록

    • 메서드 필터링

    • 응답 형식 분석

구성

환경 변수:

  • BASE_URL : API의 기본 경로(기본값: '')

  • AUTH_TOKEN : 인증을 위한 전달 토큰

  • PORT : 서버 포트(기본값: 3000)

  • SWAGGER_URL : 기본 Swagger 문서 URL

API 엔드포인트

API 탐색

curl -X POST http://localhost:3000/api/explore \ -H "Authorization: Bearer your-token" \ -H "Content-Type: application/json" \ -d '{ "url": "http://your-swagger-url", "options": { "paths": true, "schemas": true } }'

스키마 세부 정보 가져오기

curl -X POST http://localhost:3000/api/schema-details \ -H "Authorization: Bearer your-token" \ -H "Content-Type: application/json" \ -d '{ "url": "http://your-swagger-url", "schemaName": "Pet" }'

응답 스키마 가져오기

curl -X POST http://localhost:3000/api/response-schemas \ -H "Authorization: Bearer your-token" \ -H "Content-Type: application/json" \ -d '{ "url": "http://your-swagger-url", "path": "/pets", "method": "post" }'

응답 형식

미니멀 포맷

{ "status": "success", "data": { // Only non-null values } }

자세한 형식

{ "status": "success", "timestamp": "2025-01-29T10:00:00.000Z", "data": { // Full response }, "metadata": { "version": "1.0", "format": "detailed" } }

일반적인 사용 사례

  1. API 문서 검토

    Human: Can you summarize all the available endpoints and their purposes?
  2. 스키마 검증

    Human: What fields are required for creating a new pet?
  3. 반응 분석

    Human: What are the possible error responses for the login endpoint?
  4. 통합 계획

    Human: How should I structure my request to create a new order?

문제 해결

  1. 연결 문제

    • Swagger URL에 액세스할 수 있는지 확인하세요.

    • 인증 토큰이 올바른지 확인하세요

    • 포트가 사용 중이 아닌지 확인하세요

  2. 권한 부여 오류

    • AUTH_TOKEN이 올바르게 설정되었는지 확인하세요

    • 베어러 토큰이 요청에 포함되어 있는지 확인하세요.

  3. 스키마를 찾을 수 없습니다

    • 스키마 이름이 정확히 일치하는지 확인하세요

    • Swagger 사양이 올바르게 로드되었는지 확인하세요.

보안 참고 사항

  1. AUTH_TOKEN이 설정된 경우 MCP는 인증을 요구합니다.

  2. 모든 요청은 디버깅을 위해 기록됩니다.

  3. 민감한 정보는 캐시되지 않습니다.

  4. 남용을 방지하기 위해 속도 제한이 적용됩니다.

개발

기여하거나 수정하려면:

  1. 저장소를 복제합니다

  2. 종속성 설치:

    npm install
  3. 짓다:

    npm run build
  4. 로컬로 실행:

    npm start

특허

MIT 라이선스 - 자세한 내용은 라이선스 파일을 참조하세요.

-
security - not tested
F
license - not found
-
quality - not tested

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/johnneerdael/swagger-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server