This paper analyzes the security vulnerabilities of the Model Context Protocol (MCP), identifying tool poisoning as the most critical client-side threat, and proposes a multi-layered defense strategy.

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fid…

This paper introduces a component-centric framework and a novel detector, Connor, to understand and detect sophisticated, multi-component attacks targeting the Model Context Protocol (MCP) servers.

The paper introduces a defense-placement taxonomy for the Model Context Protocol (MCP) to systematically analyze security gaps, revealing that many vulnerabilities stem from architectural misalignment…

This paper investigates Description-Code Inconsistency (DCI) in Model Context Protocol (MCP) servers, finding that 9.93% of real-world tools exhibit inconsistencies that create security blind spots.

The paper introduces mcp-attested, a security extension to the Model Context Protocol (MCP) that allows hosts to safely admit and restrict the tools used by external, third-party tool servers.

This paper introduces MCP-38, a novel, protocol-specific threat taxonomy of 38 categories designed to address critical, unaddressed attack surfaces within the Model Context Protocol (MCP) system.

This study provides the first measurement of authentication security in real-world remote Model Context Protocol (MCP) servers, finding pervasive and critical authentication weaknesses, particularly i…

The paper empirically analyzes the susceptibility of seven widely used AI-assisted development tools (MCP clients) to prompt injection via tool-poisoning, revealing significant disparities in their se…

The paper identifies Mid-Session Tool Injection (MSTI) as a novel threat in the WebMCP protocol, demonstrating that attackers can manipulate the visible or perceived set of tools available to AI agent…

MCPThreatHive is an open-source platform that automates the entire threat intelligence lifecycle for Model Context Protocol (MCP) agentic systems, addressing critical gaps in current security tooling.

The paper introduces MCPSHIELD, a comprehensive formal security framework that systematically characterizes and provides a defense-in-depth architecture for the rapidly adopted but insecure Model Cont…

This paper introduces a new benchmark to test Tool Description Poisoning (TDP) attacks on LLM agents, demonstrating that even advanced models like GPT-4o are highly vulnerable and that current defense…

The paper introduces ClawTrap, a MITM-based red-teaming framework, to evaluate the security robustness of web agents like OpenClaw against dynamic, real-world network attacks, finding that model stren…

The paper proposes a graph-based framework for detecting attacks in LLM agent tool-call traffic, finding that content-level embeddings are crucial for high accuracy and that tree ensembles on these em…

This paper develops and evaluates supervised machine learning models to detect malicious tool descriptions within the Model Context Protocol (MCP), achieving high detection rates in both binary and mu…

ChainCaps introduces a novel runtime capability budgeting system that prevents 'permission laundering' in complex tool-using agents, significantly reducing attack success rates while maintaining benig…

The paper proposes CASCADE, a novel three-tiered, fully local defense architecture for detecting prompt injection and tool poisoning attacks in Model Context Protocol (MCP)-based LLM systems, achievin…

The Device Context Protocol (DCP) introduces a compact, safety-first communication standard designed to allow LLMs to reliably control resource-constrained physical microcontrollers, significantly imp…

The paper introduces mcp-sec-audit, a comprehensive toolkit that assesses Model Context Protocol (MCP) servers for over-privileged and insecure tool capabilities.