arxiv6.0 / 10

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

Donghang Duan, Qingyu Liu, Yifei Liu, Na Zou, Xia Hu, Dongrui Liu

Abstract

Large language model (LLM)-based agents interact with external tools through protocols such as the Model Context Protocol (MCP), producing tool-call traces that may expose behavioral signals about users. In this work, we systematically study the risk of user-profile inference from MCP tool-call traces, where observers infer user attributes from protocol-valid tool interactions without access to user conversations. We introduce PrivacyTrace, a benchmark containing 1,000 synthetic user profiles and 4,000 agent trajectories across four domains, generated with real MCP tools from 25 servers. Experiments with four mainstream LLM attackers show that tool-call traces enable a 26.25% attack success rate for profile inference, compared with 17.97% from prior-based guessing. Further analysis reveals that tool arguments and returned results provide the main trace-grounded evidence, while linking traces across sessions further amplifies profiling risk. These findings demonstrate that MCP tool-call traces can act as effective behavioral side channels for user profiling, motivating the development of privacy-aware mechanisms for agent-tool interactions. Code and data are available at https://github.com/AI45Lab/PrivacyTrace.

Research area

agentic aibenchmarksprivacy
Published
30 Oct 2026
Source
arxiv
Org
Shanghai Artificial Intelligence Laboratory
View paper
Sign in to read and join the discussion.
How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces — Damaqu