MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers
Zhiqiang Wang, Yichao Gao, Yanting Wang, Suyuan Liu, Haifeng Sun, Haoran Cheng, Guanquan Shi, Haohua Du, Xiangyang Li

TL;DR
This paper introduces MCPTox, a comprehensive benchmark for evaluating the vulnerability of LLM agents to Tool Poisoning attacks within the Model Context Protocol, revealing widespread susceptibility and highlighting safety challenges.
Contribution
It presents the first large-scale, systematic benchmark for Tool Poisoning in MCP settings, including attack templates and evaluation on real-world MCP servers and tools.
Findings
High attack success rate of 72.8% on vulnerable agents.
More capable models are more susceptible to Tool Poisoning.
Existing safety measures rarely refuse malicious tool instructions.
Abstract
By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due to untrusted external tools. While prior work has focused on attacks injected through external tool outputs, we investigate a more fundamental vulnerability: Tool Poisoning, where malicious instructions are embedded within a tool's metadata without execution. To date, this threat has been primarily demonstrated through isolated cases, lacking a systematic, large-scale evaluation. We introduce MCPTox, the first benchmark to systematically evaluate agent robustness against Tool Poisoning in realistic MCP settings. MCPTox is constructed upon 45 live, real-world MCP servers and 353 authentic tools. To achieve this, we design three distinct attack…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Security and Verification in Computing · Advanced Malware Detection Techniques
