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.
Servidores relacionados
Scout Monitoring MCP
patrocinadorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
velixar-mcp-server
Persistant AI Memory
AgentExecMCP
A secure, Docker-based server providing core execution capabilities for AI agents.
Neovim MCP Server
Connects any MCP client to the Neovim editor for seamless integration and control.
Aluvia
The Aluvia MCP server exposes browser session management, geo-targeting, and account operations as Model Context Protocol tools for AI agents.
iOS Device Control
An MCP server to control iOS simulators and real devices, enabling AI assistant integration on macOS.
Hyperliquid
Interact with the Hyperliquid decentralized exchange by integrating its SDK.
Unified.to MCP Server
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs.
Text2Sim MCP Server
A multi-paradigm simulation engine for Discrete-Event and System Dynamics, enabling natural language-based simulations via MCP.
Authless Remote MCP Server
An authentication-free, remote MCP server designed for deployment on Cloudflare Workers.
Gru Sandbox
Gru-sandbox(gbox) is an open source project that provides a self-hostable sandbox for MCP integration or other AI agent usecases.