MCP OpenAPI Schema Explorer

@kadykov

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

kadykov

MCP OpenAPI Schema Explorer について

MCP server providing token-efficient access to OpenAPI/Swagger specs via MCP Resource Templates for client-side exploration.

#nodejs #development #node #typescript #mcp #swagger #openapi #developer-tools #node-js#api-specification#model-context-protocol #mcp-server

MCP OpenAPI Schema Explorer の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "My API Spec (npx)": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-openapi-schema-explorer@latest",
        "https://petstore3.swagger.io/api/v3/openapi.json",
        "--output-format",
        "yaml"
      ],
      "env": {}
    }
  }
}

MCP OpenAPI Schema Explorer のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is MCP OpenAPI Schema Explorer?

MCP OpenAPI Schema Explorer is an MCP (Model Context Protocol) server that provides token-efficient access to OpenAPI v3.0 and Swagger v2.0 specifications via MCP Resource Templates. It allows MCP clients like Cline or Claude Desktop to explore large API specifications without loading the entire file into an LLM’s context window.

How to use MCP OpenAPI Schema Explorer?

Add a configuration entry to your MCP client’s mcpServers settings, using either npx (recommended), Docker, a global npm install, or a local build. The server takes a path or URL to a specification and optional flags like --output-format. Multiple specifications can be added as separate server entries.

Key features of MCP OpenAPI Schema Explorer

Exposes OpenAPI specs via parameterized MCP resource templates (openapi://...).
Loads local files and remote HTTP/HTTPS URLs.
Converts Swagger v2.0 to OpenAPI v3.0 automatically.
Supports JSON, YAML, and minified JSON output formats.
Transforms internal $refs into clickable MCP URIs.
Server name in clients reflects the specification’s info.title.

Use cases of MCP OpenAPI Schema Explorer

Explore a 500+ endpoint API without blowing the LLM context window.
Let an AI agent dynamically discover and read specific path or component details.
Compare multiple API specifications by adding separate server entries.
Integrate with Claude Desktop, Cline, or Windsurf for interactive API understanding.

よくある質問

How does this server differ from tool-based OpenAPI servers?

This server uses MCP Resource Templates instead of tools, providing read-only, on-demand access to specific parts of the spec without pre-enumerating thousands of paths. This can be more token-efficient for LLM interactions.

What OpenAPI versions are supported?

OpenAPI v3.0 and Swagger v2.0 are supported. Swagger v2.0 specifications are automatically converted to v3.0 upon loading.

Can I use multiple API specifications at once?

Yes. Add separate entries in your client’s `mcpServers` configuration, each with a unique name and pointing to a different specification.

How do I change the output format?

Use the `--output-format` flag with one of: `json` (default), `yaml`, or `json-minified`.

Do I need to install the server first?

No. When using the recommended `npx` or Docker methods, the server is automatically downloaded or pulled when your MCP client starts.

「その他」の他のコンテンツ

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct