Human-AI collaboration faces growing challenges as AI systems increasingly outperform humans on complex tasks, while humans remain responsible for orchestration, validation, and decision oversight. To address this imbalance, we introduce Human Tool, an MCP-style interface abstraction, building on recent Model Context Protocol designs, that exposes humans as callable tools within AI-led, proactive workflows. Here, "tool" denotes a coordination abstraction, not a reduction of human authority or responsibility. Building on LLM-based agent architectures, we operationalize Human Tool by modeling human contributions through structured tool schemas of capabilities, information, and authority. These schemas enable agents to dynamically invoke human input based on relative strengths and reintegrate it through efficient, natural interaction protocols. We validate the framework through controlled studies in both decision-making and creative tasks, demonstrating improved task performance, reduced human workload, and more balanced collaboration dynamics compared to baseline systems. Finally, we discuss implications for human-centered AI design, highlighting how MCP-style human tools enable strong AI leadership while amplifying uniquely human strengths.

翻译：随着人工智能系统在复杂任务上日益超越人类，而人类仍需负责协调、验证与决策监督，人机协作面临日益严峻的挑战。为解决这种失衡，我们提出人类工具——一种基于近期模型上下文协议设计的MCP风格接口抽象，将人类作为可调用工具暴露于AI主导的主动工作流中。此处“工具”指代协调抽象，而非对人类权威或责任的削弱。基于大语言模型的智能体架构，我们通过结构化工具模式（涵盖能力、信息与权限）对人类贡献进行建模，从而实现人类工具的操作化。这些模式使智能体能依据相对优势动态调用人类输入，并通过高效自然的交互协议进行重新整合。我们在决策与创意任务中通过对照研究验证了该框架，结果表明相较于基线系统，其能提升任务性能、减轻人类工作量并实现更均衡的协作动态。最后，我们探讨了该设计对人本人工智能的启示，强调MCP风格的人类工具如何在强化AI主导作用的同时，放大人类独有的优势。