OpenAPI Kubernetes

About

A lightweight Model Context Protocol (MCP) server that runs inside your Kubernetes cluster, crawls your Services and endpoints via the Kubernetes API, auto-detects exposed OpenAPI specs, and builds a live, queryable index of your entire microservice surface area. It normalizes each spec (derefs, merges, fixes inconsistencies), tracks versions, and exposes the whole thing as MCP tools so agents can introspect, list, and invoke endpoints directly over in-cluster networking — essentially turning your microservices into a distributed, self-describing function registry.

Key Features

• Fetching and parsing of OpenAPI/Swagger specifications
• Embedded Apache Derby database for persistence (no external DB required)
• Configurable scheduled refresh of microservice data
• Exposure of type-safe tools via Model Context Protocol (MCP)
• 0 GitHub stars
• Automatic Discovery of services in Kubernetes namespaces

Use Cases

• Providing a standardized interface for external and internal tools to query and manage microservice APIs.
• Enabling AI agents and LLMs to discover and interact with internal Kubernetes microservices programmatically.
• Creating a dynamic, self-updating API registry for in-cluster service introspection.
• Facilitating automated testing and integration of microservices by allowing direct in-cluster endpoint invocation.