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

**Authors:** Donghang Duan, Qingyu Liu, Yifei Liu, Na Zou, Xia Hu, Dongrui Liu  
**Lab:** Shanghai AI Lab · **Published:** 30 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.41885) · [PDF](https://arxiv.org/pdf/2610.41885) · [Code](https://github.com/AI45Lab/PrivacyTrace) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.41885.html)

## Key numbers

- **26.25%**: …mainstream LLM attackers show that tool-call traces enable a 26.25% attack success rate for profile inference
- **17.97%**: compared with 17.97% from prior-based guessing
- **4,000**: a benchmark containing 1,000 synthetic user profiles and 4,000 agent trajectories across four domains

## 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.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.