OpenAPI MCP Server
About
Explore and analyze OpenAPI specifications from local files or remote URLs.
Details
- Author
- sagenkoder
- Categories
- Developer Tools, API, Knowledge Base
Jump to
Setup
Install OpenAPI MCP Server in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/sagenkoder/go-openapi-exploration-mcp-server
Follow the installation instructions in the repository README, then restart your MCP client.
A Model Context Protocol (MCP) server that enables LLMs to explore and understand OpenAPI specifications through structured tools.
- πSmart API Exploration- Navigate APIs by categories, endpoints, and schemas
- πMultiple Modes- Run as stdio (for Claude Desktop), HTTP server, or interactive CLI
- πΎIntelligent Caching- Caches remote OpenAPI specs for faster access
- ποΈMulti-Architecture- Supports Linux AMD64 and ARM64
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.jsonon 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"] } } }
{ "mcpServers": { "openapi": { "command": "/path/to/openapi-mcp-stdio", "env": { "OPENAPI_SPEC_URL": "https://api.example.com/openapi.json" } } } }
# 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
- openapi-mcp-stdio-linux-amd64- MCP stdio mode
- openapi-mcp-http-linux-amd64- HTTP server mode
- openapi-mcp-interactive-linux-amd64- Interactive CLI mode
# 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
- OPENAPI_SPEC_URL(required) - URL or file path to OpenAPI spec
- OPENAPI_CACHE_DIR(optional) - Cache directory (default:~/.openapi-mcp-cache)
# 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
# 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
# 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
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
OPENAPI_SPEC_URL=/path/to/openapi.yaml ./openapi-mcp-stdio
OPENAPI_CACHE_DIR=/tmp/api-cache \ OPENAPI_SPEC_URL=https://api.example.com/openapi.json \ ./openapi-mcp-stdio
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
cmd/ βββ openapi-mcp-stdio/ # MCP stdio mode βββ openapi-mcp-http/ # HTTP server mode βββ openapi-mcp-interactive/ # Interactive CLI mode internal/ βββ cache.go # Caching logic βββ handlers.go # MCP tool handlers βββ server.go # Core server logic βββ utils.go # Utilities
# Build specific mode docker build --build-arg MODE=stdio -t my-openapi-mcp:stdio . # Build all modes ./build.sh docker
MIT License - seeLICENSEfile for details.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Converts OpenAPI/Swagger specifications to Model Context Protocol (MCP) format, providing a modern Web UI and a backend service.
A server that converts OpenAPI specifications into the Model Context Protocol (MCP).
Serves multiple OpenAPI specifications to enable LLM-powered IDE integrations.
A server for splitting and extracting parts of OpenAPI specifications using Redocly CLI.
MCP server for API documentation, supporting GraphQL, OpenAPI/Swagger, and gRPC from local files or remote URLs
One shared context layer for AI agents and humans β live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.
The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.
A server that dynamically creates MCP endpoints from any OpenAPI specification URL.
A TypeScript MCP server to access Apifox API data via Stdio.
Provides API documentation from Apifox projects as a data source for AI programming tools that support MCP.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





