Model Context Protocol (MCP)
Model Context Protocol (MCP) is an open standard developed by Anthropic for connecting large language model (LLM) agents to external data sources, APIs, and tools through a standardized server-client interface. In the PLM context, MCP enables AI agents to query BOM data, change management records, simulation results, and supplier data from existing PLM, ERP, and MES systems without requiring custom integration code for each data source.
Why it matters
MCP is the infrastructure layer that makes multi-agent PLM orchestration practical. Instead of hand-coding a new integration each time an AI agent needs to read from Windchill or write to SAP, developers expose those systems as MCP servers, and any MCP-capable agent can connect. For industrial software, MCP represents the same standardization step that REST APIs provided for web services — a common protocol that shifts the integration burden from individual vendors to a shared standard.
External References
This term appears in
Cite this definition
Finocchiaro, Michael. “Model Context Protocol (MCP).” DemystifyingPLM PLM Glossary, 2026, https://www.demystifyingplm.com/glossary/model-context-protocol-mcp