Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol

arXiv:2605.00827v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly interact with external systems through tool-calling protocols such as the Model Context Protocol (MCP). In prevailing architectures, the agent must reason about every tool invocation in every session, consuming tokens proportional to the number of actions performed--even when the task has been solved before. We present the MCP Workflow Engine, a novel MCP-native orchestration layer that decouples int