IoT-MCP：透過模型上下文協議橋接大型語言模型與物聯網系統

摘要

大型语言模型（LLMs）与物联网（IoT）系统的集成在硬件异构性和控制复杂性方面面临重大挑战。模型上下文协议（MCP）作为关键推动者，提供了LLMs与物理设备之间的标准化通信。我们提出了IoT-MCP，一种通过边缘部署服务器实现MCP的新颖框架，以桥接LLMs与IoT生态系统。为了支持严格的评估，我们引入了IoT-MCP Bench，这是首个包含114个基本任务（例如，“当前温度是多少？”）和1,140个复杂任务（例如，“我感觉很热，你有什么建议吗？”）的基准测试，适用于支持IoT的LLMs。在22种传感器类型和6种微控制器单元上的实验验证表明，IoT-MCP在生成完全符合预期的工具调用并获得完全准确结果的任务成功率达到了100%，平均响应时间为205毫秒，峰值内存占用为74KB。这项工作不仅提供了一个开源集成框架（https://github.com/Duke-CEI-Center/IoT-MCP-Servers），还为LLM-IoT系统提供了一种标准化的评估方法。

English

The integration of Large Language Models (LLMs) with Internet-of-Things (IoT) systems faces significant challenges in hardware heterogeneity and control complexity. The Model Context Protocol (MCP) emerges as a critical enabler, providing standardized communication between LLMs and physical devices. We propose IoT-MCP, a novel framework that implements MCP through edge-deployed servers to bridge LLMs and IoT ecosystems. To support rigorous evaluation, we introduce IoT-MCP Bench, the first benchmark containing 114 Basic Tasks (e.g., ``What is the current temperature?'') and 1,140 Complex Tasks (e.g., ``I feel so hot, do you have any ideas?'') for IoT-enabled LLMs. Experimental validation across 22 sensor types and 6 microcontroller units demonstrates IoT-MCP's 100% task success rate to generate tool calls that fully meet expectations and obtain completely accurate results, 205ms average response time, and 74KB peak memory footprint. This work delivers both an open-source integration framework (https://github.com/Duke-CEI-Center/IoT-MCP-Servers) and a standardized evaluation methodology for LLM-IoT systems.

IoT-MCP：透過模型上下文協議橋接大型語言模型與物聯網系統

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol

摘要

Support