Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review

TL;DR

This survey reviews how classical software design patterns can improve communication reliability and scalability in LLM-driven multi-agent systems using the Model Context Protocol, highlighting architectural strategies, applications, and future challenges.

Contribution

It provides a comprehensive analysis of integrating traditional design patterns with MCP to enhance LLM agent communication frameworks, including conceptual models and real-world applications.

Findings

Design patterns like Mediator and Observer are relevant for MCP-based LLM communication.

Architectural variations support different levels of agent autonomy.

Applications in finance demonstrate practical benefits of these patterns.

Abstract

This survey investigates how classical software design patterns can enhance the reliability and scalability of communication in Large Language Model (LLM)-driven agentic AI systems, focusing particularly on the Model Context Protocol (MCP). It examines the foundational architectures of LLM-based agents and their evolution from isolated operation to sophisticated, multi-agent collaboration, addressing key communication hurdles that arise in this transition. The study revisits well-established patterns, including Mediator, Observer, Publish-Subscribe, and Broker, and analyzes their relevance in structuring agent interactions within MCP-compliant frameworks. To clarify these dynamics, the article provides conceptual schematics and formal models that map out communication pathways and optimize data flow. It further explores architectural variations suited to different degrees of agent autonomy and system complexity. Real-world applications in domains such as real-time financial processing and investment banking are discussed, illustrating how these patterns and MCP can meet specific operational demands. The article concludes by outlining open challenges, potential security risks, and promising directions for advancing robust, interoperable, and scalable multi-agent LLM ecosystems.