MMS use RESTful API for both inference and management calls. The API is compliance with OpenAPI specification 3.0. User can easily generate client side code for Java, Scala, C#, Javascript use swagger codegen.
When MMS startup, it start two web services:
By default, MMS listening on 8080 port for Inference API and 8081 on Management API. Both API is only accessible from localhost. Please see MMS Configuration for how to enable access from remote host.