OpenAPI MCP Server
Explore and analyze OpenAPI specifications from local files or remote URLs.
OpenAPI MCP Server
A Model Context Protocol (MCP) server that enables LLMs to explore and understand OpenAPI specifications through structured tools.
Features
- 🔍 Smart API Exploration - Navigate APIs by categories, endpoints, and schemas
- 🚀 Multiple Modes - Run as stdio (for Claude Desktop), HTTP server, or interactive CLI
- 💾 Intelligent Caching - Caches remote OpenAPI specs for faster access
- 🏗️ Multi-Architecture - Supports Linux AMD64 and ARM64
Quick Start
Using Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"openapi": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "OPENAPI_SPEC_URL=https://api.example.com/openapi.json", "ghcr.io/sagenkoder/go-openapi-exploration-mcp-server:latest"]
}
}
}
Or use a local binary:
{
"mcpServers": {
"openapi": {
"command": "/path/to/openapi-mcp-stdio",
"env": {
"OPENAPI_SPEC_URL": "https://api.example.com/openapi.json"
}
}
}
}
Installation
Docker (Recommended)
# Latest (stdio mode)
docker pull ghcr.io/sagenkoder/go-openapi-exploration-mcp-server:latest
# Specific modes
docker pull ghcr.io/sagenkoder/go-openapi-exploration-mcp-server:http
docker pull ghcr.io/sagenkoder/go-openapi-exploration-mcp-server:interactive
Download Binaries
Download from releases:
openapi-mcp-stdio-linux-amd64- MCP stdio modeopenapi-mcp-http-linux-amd64- HTTP server modeopenapi-mcp-interactive-linux-amd64- Interactive CLI mode
Build from Source
# Clone
git clone https://github.com/SagenKoder/go-openapi-exploration-mcp-server.git
cd go-openapi-exploration-mcp-server
# Build all modes
./build.sh
# Or build specific mode
go build -o openapi-mcp-stdio ./cmd/openapi-mcp-stdio
Usage
Environment Variables
OPENAPI_SPEC_URL(required) - URL or file path to OpenAPI specOPENAPI_CACHE_DIR(optional) - Cache directory (default:~/.openapi-mcp-cache)
Stdio Mode (for MCP clients)
# Docker
docker run -i --rm \
-e OPENAPI_SPEC_URL=https://petstore3.swagger.io/api/v3/openapi.json \
ghcr.io/sagenkoder/go-openapi-exploration-mcp-server:latest
# Binary
OPENAPI_SPEC_URL=https://petstore3.swagger.io/api/v3/openapi.json ./openapi-mcp-stdio
HTTP Mode
# Docker
docker run -p 8080:8080 \
-e OPENAPI_SPEC_URL=https://petstore3.swagger.io/api/v3/openapi.json \
ghcr.io/sagenkoder/go-openapi-exploration-mcp-server:http
# Binary
OPENAPI_SPEC_URL=https://petstore3.swagger.io/api/v3/openapi.json ./openapi-mcp-http -addr :8080
Interactive Mode
# Docker
docker run -it --rm \
-e OPENAPI_SPEC_URL=https://petstore3.swagger.io/api/v3/openapi.json \
ghcr.io/sagenkoder/go-openapi-exploration-mcp-server:interactive
# Binary
OPENAPI_SPEC_URL=https://petstore3.swagger.io/api/v3/openapi.json ./openapi-mcp-interactive
Available Tools
The server provides these tools to LLMs:
- list_categories - List API categories based on path segments
- list_endpoints - List endpoints, optionally filtered by category
- show_endpoint - Show detailed endpoint information including parameters and schemas
- get_spec_info - Get general information about the API
- show_schema - Inspect specific schema components
Examples
Local File
OPENAPI_SPEC_URL=/path/to/openapi.yaml ./openapi-mcp-stdio
With Custom Cache
OPENAPI_CACHE_DIR=/tmp/api-cache \
OPENAPI_SPEC_URL=https://api.example.com/openapi.json \
./openapi-mcp-stdio
Docker with Volume Mount
docker run -i --rm \
-v $(pwd)/openapi.yaml:/openapi.yaml:ro \
-e OPENAPI_SPEC_URL=/openapi.yaml \
ghcr.io/sagenkoder/go-openapi-exploration-mcp-server:latest
Development
Project Structure
cmd/
├── openapi-mcp-stdio/ # MCP stdio mode
├── openapi-mcp-http/ # HTTP server mode
└── openapi-mcp-interactive/ # Interactive CLI mode
internal/
├── cache.go # Caching logic
├── handlers.go # MCP tool handlers
├── server.go # Core server logic
└── utils.go # Utilities
Building Docker Images
# Build specific mode
docker build --build-arg MODE=stdio -t my-openapi-mcp:stdio .
# Build all modes
./build.sh docker
License
MIT License - see LICENSE file for details.
相關伺服器
Alpha Vantage MCP Server
贊助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Shrike Security
AI agent security scanner — protect LLM-powered apps from prompt injection, SQL injection, data exfiltration, and adversarial attacks via MCP.
Codex MCP Wrapper
An MCP server that wraps the OpenAI Codex CLI, exposing its functionality through the MCP API.
Aptos MCP Server
Interact with Aptos documentation and create full-stack Aptos blockchain applications.
Hashkey MCP Server
Provides onchain tools for AI applications to interact with the Hashkey Network.
Skills-ContextManager
Don’t pollute your AI agent’s context with 1,000 skills. Use Skills-ContextManager, a self-hosted web UI for managing AI skills and workflows by providing skills to an AI agent via MCP only when needed. Simply add skills to your library and enable or disable them with a toggle. Choose whether a skill is always loaded into context or dynamically activated when the AI agent determines it’s needed.
ChuckNorris
A specialized MCP gateway for LLM enhancement prompts and jailbreaks with dynamic schema adaptation. Provides prompts for different LLMs using an enum-based approach.
WCAG Aria patterns MCP
MCP server for WCAG practices found at https://github.com/karanshah229/wcag-aria-practices-mcp-skill/tree/main
Remote MCP Server (Authless)
An example of a remote MCP server without authentication, deployable on Cloudflare Workers.
vnsh
Ephemeral encrypted file sharing for AI. Client-side AES-256 encryption, 24h auto-vaporization.
Claude Memory MCP Server
A persistent memory server for Large Language Models, designed to integrate with the Claude desktop application. It supports tiered memory, semantic search, and automatic memory management.