Beyond Formal Semantics for Capabilities and Skills: Model Context Protocol in Manufacturing

TL;DR

This paper introduces the Model Context Protocol (MCP), enabling LLMs to access manufacturing system functionalities directly, reducing manual effort and enhancing flexibility in industrial automation.

Contribution

It presents MCP as a novel standardized interface for exposing system capabilities to LLMs, demonstrated through a prototype in manufacturing automation.

Findings

MCP allows LLMs to plan and execute multi-step manufacturing processes.

The approach reduces reliance on explicit semantic models.

Prototype shows potential for flexible, automated industrial systems.

Abstract

Explicit modeling of capabilities and skills -- whether based on ontologies, Asset Administration Shells, or other technologies -- requires considerable manual effort and often results in representations that are not easily accessible to Large Language Models (LLMs). In this work-in-progress paper, we present an alternative approach based on the recently introduced Model Context Protocol (MCP). MCP allows systems to expose functionality through a standardized interface that is directly consumable by LLM-based agents. We conduct a prototypical evaluation on a laboratory-scale manufacturing system, where resource functions are made available via MCP. A general-purpose LLM is then tasked with planning and executing a multi-step process, including constraint handling and the invocation of resource functions via MCP. The results indicate that such an approach can enable flexible industrial automation without relying on explicit semantic models. This work lays the basis for further exploration of external tool integration in LLM-driven production systems.