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

arXiv: https://arxiv.org/abs/2506.11180 · HTML: https://mlsanity.com/paper/2506.11180/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 7 of 7)

- [Large Language Models for Multi-Robot Systems: A Survey](https://mlsanity.com/paper/2502.03814/) (2025)
- [LLM-Powered AI Agent Systems and Their Applications in Industry](https://mlsanity.com/paper/2505.16120/) (2025)
- [Autonomous Industrial Control using an Agentic Framework with Large Language Models](https://mlsanity.com/paper/2411.05904/) (2024)
- [Control Industrial Automation System with Large Language Model Agents](https://mlsanity.com/paper/2409.18009/) (2024)
- [A Reference Model for Common Understanding of Capabilities and Skills in Manufacturing](https://mlsanity.com/paper/2209.09632/) (2022)
- [Toward a Method to Generate Capability Ontologies from Natural Language Descriptions](https://mlsanity.com/paper/2406.07962/) (2024)
- [Capability-Driven Skill Generation with LLMs: A RAG-Based Approach for Reusing Existing Libraries and Interfaces](https://mlsanity.com/paper/2505.03295/) (2025)

## Built on by (most cited first, 4 of 4)

- [Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol](https://mlsanity.com/paper/2512.03955/) (2025)
- [Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering](https://mlsanity.com/paper/2606.09182/) (2026)
- [Towards an Intention Abstraction Layer for Autonomous Industrial Systems](https://mlsanity.com/paper/2607.14553/) (2026)
- [LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing](https://mlsanity.com/paper/2610.01364/) (2026)

## Abstract (arXiv)

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.