OpenAPI MCP Server

OpenAPI MCP Server

Exposes OpenAPI specifications as MCP tools, enabling AI assistants to explore and understand API structures, endpoints, schemas, and documentation through semantic queries.

Category
Visit Server

README

opamcp

"OpenAPI 스펙 문서 읽기 귀찮아..." 하던 AI를 위한 MCP 서버

OpenAPI 스펙 URL 하나 던져주면, AI가 알아서 API 구조를 탐색할 수 있게 해주는 도구입니다. 더 이상 "이 API 어떻게 쓰는 거야?" 라고 물을 때마다 스펙 문서 전체를 붙여넣지 않아도 됩니다.

어떻게 쓰나요?

npx -y opamcp https://petstore3.swagger.io/api/v3/openapi.json

끝. 진짜 이게 다입니다.

Claude Desktop / Cursor 설정

{
  "mcpServers": {
    "my-api": {
      "command": "npx",
      "args": ["-y", "opamcp", "https://your-api.com/openapi.json"]
    }
  }
}

뭘 할 수 있나요?

도구 하는 일
get_api_info API가 뭐하는 녀석인지 한눈에 파악
list_tags API 그룹(태그) 목록 보기
list_endpoints 전체 엔드포인트 훑어보기
get_endpoints_by_tag 특정 태그의 엔드포인트만 보기
get_endpoint_detail 엔드포인트 하나 깊게 파보기
list_schemas 어떤 데이터 타입들이 있는지 보기
get_schema 특정 스키마 정의 자세히 보기
search_endpoints 키워드로 엔드포인트 검색
refresh_spec 스펙 변경됐으면 새로고침

이렇게 쓰면 됩니다

나: "이 API 뭐야?"
AI: (get_api_info 호출) "아, 펫샵 API네요. 반려동물 관리하는..."

나: "주문 관련 API 있어?"
AI: (search_endpoints 'order' 호출) "네, 주문 생성, 조회, 삭제 API가 있네요"

나: "주문 생성 어떻게 해?"
AI: (get_endpoint_detail '/store/order' 'post' 호출) "이렇게 하시면 됩니다..."

개발

bun install          # 의존성 설치
bun run dev <url>    # 로컬 실행
bun run build        # 빌드

라이선스

MIT - 맘대로 쓰세요


English

For AIs tired of reading OpenAPI spec documents

Just give it an OpenAPI spec URL, and your AI can explore the API structure on its own. No more pasting entire spec documents every time someone asks "how do I use this API?"

Quick Start

npx -y opamcp https://petstore3.swagger.io/api/v3/openapi.json

That's it. Really.

Claude Desktop / Cursor Setup

{
  "mcpServers": {
    "my-api": {
      "command": "npx",
      "args": ["-y", "opamcp", "https://your-api.com/openapi.json"]
    }
  }
}

What can it do?

Tool What it does
get_api_info Get the gist of what this API is about
list_tags See how the API is organized
list_endpoints Browse all endpoints
get_endpoints_by_tag Filter endpoints by tag
get_endpoint_detail Deep dive into a specific endpoint
list_schemas See what data types exist
get_schema Get the full schema definition
search_endpoints Find endpoints by keyword
refresh_spec Reload spec if it changed

How it works

You: "What's this API?"
AI: (calls get_api_info) "It's a pet store API for managing pets..."

You: "Any order-related endpoints?"
AI: (calls search_endpoints 'order') "Yes, there's create, get, and delete order APIs"

You: "How do I create an order?"
AI: (calls get_endpoint_detail '/store/order' 'post') "Here's how..."

Development

bun install          # Install deps
bun run dev <url>    # Run locally
bun run build        # Build

License

MIT - Do whatever you want

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured