Human Tool: An MCP-Style Framework for Human-Agent Collaboration

TL;DR

This paper introduces Human Tool, a framework that integrates humans as callable tools within AI workflows, enhancing collaboration, decision-making, and workload management in human-AI teams.

Contribution

It presents a novel MCP-style interface abstraction that models human contributions as structured schemas, enabling dynamic invocation and natural interaction within AI systems.

Findings

Improved task performance in decision-making and creative tasks.

Reduced human workload during collaboration.

More balanced human-AI interaction dynamics.

Abstract

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.