Beyond Formal Semantics for Capabilities and Skills: Model Context Protocol in Manufacturing
This work addresses automation challenges in manufacturing by reducing manual modeling efforts, though it is incremental as it builds on existing MCP technology.
The paper tackles the problem of manual effort and LLM accessibility in modeling capabilities and skills for manufacturing by proposing the Model Context Protocol (MCP) as an alternative, with a prototype evaluation showing it enables flexible industrial automation without explicit semantic models.
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.