MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols
By: Yixuan Yang, Daoyuan Wu, Yufan Chen
Potential Business Impact:
Finds security flaws in AI tools.
Large Language Models (LLMs) are increasingly integrated into real-world applications via the Model Context Protocol (MCP), a universal, open standard for connecting AI agents with data sources and external tools. While MCP enhances the capabilities of LLM-based agents, it also introduces new security risks and expands their attack surfaces. In this paper, we present the first systematic taxonomy of MCP security, identifying 17 attack types across 4 primary attack surfaces. We introduce MCPSecBench, a comprehensive security benchmark and playground that integrates prompt datasets, MCP servers, MCP clients, and attack scripts to evaluate these attacks across three major MCP providers. Our benchmark is modular and extensible, allowing researchers to incorporate custom implementations of clients, servers, and transport protocols for systematic security assessment. Experimental results show that over 85% of the identified attacks successfully compromise at least one platform, with core vulnerabilities universally affecting Claude, OpenAI, and Cursor, while prompt-based and tool-centric attacks exhibit considerable variability across different hosts and models. Overall, MCPSecBench standardizes the evaluation of MCP security and enables rigorous testing across all MCP layers.
Similar Papers
MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
Cryptography and Security
Tests if AI can use tools safely.
MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers
Computation and Language
Tests AI safety with real-world tools.
MCP-Guard: A Defense Framework for Model Context Protocol Integrity in Large Language Model Applications
Cryptography and Security
Protects smart computer helpers from being tricked.