Swagger Explorer MCP
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=3000Related MCP server: MCP-QA
Claude Desktop 설치
클로드 데스크톱 열기
설정(기어 아이콘)을 클릭하세요
"도구 및 통합"을 선택하세요
"MCP 서버 추가"를 클릭하세요
다음을 입력하세요.
Name: Swagger Explorer Command: npx -y @johnneerdael/swagger-mcp Arguments: --swagger-url=$SWAGGER_URL"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
인증 지원
베어러 토큰 인증
환경 변수를 통해 구성 가능
사용자 정의 응답 형식
최소 형식: null/빈 값 제거
자세한 형식: 메타데이터 및 타임스탬프 포함
원시 형식: 수정되지 않은 응답
스키마 분석
자세한 부동산 탐색
응답 스키마 분석
스키마 관계
API 탐색
경로 목록
메서드 필터링
응답 형식 분석
구성
환경 변수:
BASE_URL: API의 기본 경로(기본값: '')AUTH_TOKEN: 인증을 위한 전달 토큰PORT: 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
API 문서 검토
Human: Can you summarize all the available endpoints and their purposes?스키마 검증
Human: What fields are required for creating a new pet?반응 분석
Human: What are the possible error responses for the login endpoint?통합 계획
Human: How should I structure my request to create a new order?
문제 해결
연결 문제
Swagger URL에 액세스할 수 있는지 확인하세요.
인증 토큰이 올바른지 확인하세요
포트가 사용 중이 아닌지 확인하세요
권한 부여 오류
AUTH_TOKEN이 올바르게 설정되었는지 확인하세요
베어러 토큰이 요청에 포함되어 있는지 확인하세요.
스키마를 찾을 수 없습니다
스키마 이름이 정확히 일치하는지 확인하세요
Swagger 사양이 올바르게 로드되었는지 확인하세요.
보안 참고 사항
AUTH_TOKEN이 설정된 경우 MCP는 인증을 요구합니다.
모든 요청은 디버깅을 위해 기록됩니다.
민감한 정보는 캐시되지 않습니다.
남용을 방지하기 위해 속도 제한이 적용됩니다.
개발
기여하거나 수정하려면:
저장소를 복제합니다
종속성 설치:
npm install짓다:
npm run build로컬로 실행:
npm start
특허
MIT 라이선스 - 자세한 내용은 라이선스 파일을 참조하세요.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for AI access to Swagger by SmartBear.
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA server that enables interaction with any API that has a Swagger/OpenAPI specification through Model Context Protocol (MCP), automatically generating tools from API endpoints and supporting multiple authentication methods.259 npm115Apache 2.0
- FlicenseNot gradedqualityDmaintenanceAn MCP server for the comprehensive analysis of Swagger 2.0 and OpenAPI 3.x contracts. It allows users to extract detailed information about endpoints, request/response schemas, parameters, and security configurations from API documentation.-
- AlicenseBqualityDmaintenanceAn MCP server that allows users to query and retrieve request and response JSON schemas directly from Swagger/OpenAPI specifications. It supports automatic reference resolution and path parameter matching to help AI models interact with API interfaces.18 npmMIT
- FlicenseAqualityDmaintenanceAn MCP server that lets Claude query, search, and explore OpenAPI specifications from local files. Supports OpenAPI 3.x and Swagger 2.0.4-