Swagger Explorer MCP
Swagger エクスプローラー MCP
Claude を通じて Swagger/OpenAPI 仕様を調査および分析するための管理コントロール プレーン (MCP) サーバー。
クイックスタート
npx を使用してグローバルにインストールして実行します。
npx -y @johnneerdael/swagger-mcpまたは環境変数を使用してインストールします:
npx -y @johnneerdael/swagger-mcp \
--env BASE_URL=/api \
--env AUTH_TOKEN=your-token \
--env PORT=3000Related MCP server: MCP-QA
Claude Desktopのインストール
クロードデスクトップを開く
設定(歯車アイコン)をクリックします
「ツールと統合」を選択
「MCPサーバーを追加」をクリックします
以下を入力してください:
Name: Swagger Explorer Command: npx -y @johnneerdael/swagger-mcp Arguments: --swagger-url=$SWAGGER_URL「インストール」をクリック
クロードとの使用
以下に、クロードとのやり取りの例をいくつか示します。
基本的なSwaggerの探索
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]特定のエンドポイントの分析
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]スキーマ分析
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]特徴
認証サポート
ベアラートークン認証
環境変数で設定可能
カスタムレスポンスフォーマット
最小限のフォーマット: null/空の値を削除します
詳細形式: メタデータとタイムスタンプを含む
生の形式: 変更されていない応答
スキーマ分析
詳細な物件調査
応答スキーマ分析
スキーマ関係
API探索
パスリスト
メソッドフィルタリング
回答形式の分析
構成
環境変数:
BASE_URL: APIのベースパス(デフォルト: '')AUTH_TOKEN: 認証用のベアラートークンPORT: サーバーポート(デフォルト: 3000)SWAGGER_URL: デフォルトのSwaggerドキュメントURL
APIエンドポイント
APIを探索する
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
}
}'スキーマの詳細を取得する
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"
}'レスポンススキーマを取得する
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"
}'応答形式
最小限のフォーマット
{
"status": "success",
"data": {
// Only non-null values
}
}詳細なフォーマット
{
"status": "success",
"timestamp": "2025-01-29T10:00:00.000Z",
"data": {
// Full response
},
"metadata": {
"version": "1.0",
"format": "detailed"
}
}一般的な使用例
APIドキュメントレビュー
Human: Can you summarize all the available endpoints and their purposes?スキーマ検証
Human: What fields are required for creating a new pet?応答分析
Human: What are the possible error responses for the login endpoint?統合計画
Human: How should I structure my request to create a new order?
トラブルシューティング
接続の問題
Swagger URL にアクセスできることを確認する
認証トークンが正しいか確認する
ポートが使用されていないことを確認してください
認証エラー
AUTH_TOKENが正しく設定されていることを確認する
リクエストにベアラートークンが含まれていることを確認する
スキーマが見つかりません
スキーマ名が完全に一致しているかどうかを確認する
Swagger仕様が正しくロードされていることを確認する
セキュリティノート
AUTH_TOKENが設定されている場合、MCPは認証を必要とする
すべてのリクエストはデバッグのために記録されます
機密情報はキャッシュされません
不正使用を防ぐためにレート制限が適用されます
発達
貢献または変更するには:
リポジトリをクローンする
依存関係をインストールします:
npm install建てる:
npm run buildローカルで実行:
npm start
ライセンス
MITライセンス - 詳細はLICENSEファイルを参照
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-