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

2025-06-12

AI Summary

Traditional manufacturing capability modeling relies on manually constructed ontologies or semantic models, incurring high development costs, poor scalability, and limited compatibility with large language models (LLMs) for direct invocation. Method: This paper introduces the Model Context Protocol (MCP) to manufacturing for the first time, proposing a novel, semantics-free capability exposure paradigm. By leveraging standardized MCP interfaces, LLM-based agents can directly perceive, interpret, and orchestrate heterogeneous physical device functionalities—eliminating the need for manual ontology definition. Contribution/Results: Evaluated on a laboratory-scale prototype, the approach enables constraint-aware, multi-step process planning and autonomous execution: the LLM dynamically parses task constraints, generates feasible operation sequences, and invokes underlying resource functions in real time. Experiments demonstrate the feasibility of flexible manufacturing automation without any semantic modeling, thereby overcoming a critical bottleneck in LLM–physical-world integration.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Modeling other Agents

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Reducing manual effort in modeling capabilities and skills
• Enhancing LLM accessibility to manufacturing system functionalities
• Enabling flexible automation without explicit semantic models

Innovation

• Model Context Protocol standardizes interface for LLMs
• MCP enables direct LLM-based agent functionality access
• Flexible automation without explicit semantic models