# MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI

Source: [MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI](<https://www.sota2.com/research/paper/68fa7ad71e209131cea85774>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-10T05:00:05.200Z

Authors: Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, Meng Han

Published: 2025-08-14T18:00:25.000Z

## Abstract

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak. The integration of Large Language Models (LLMs) with external tools via protocols such as the Model Context Protocol (MCP) introduces critical security vulnerabilities, including prompt injection, data exfiltration, and other threats. To counter these challenges, we propose MCP-GUARD, a robust, layered defense architecture designed for LLM-tool interactions. MCP-GUARD employs a three-stage detection pipeline that balances efficiency with accuracy: it progresses from lightweight static scanning for overt threats and a deep neural detector for semantic attacks, to our fine-tuned E5-based model which achieves 96.01\\% accuracy in identifying adversarial prompts. Finally, an LLM arbitrator synthesizes these signals to deliver the final decision. To enable rigorous training and evaluation, we introduce MCP-ATTACKBENCH, a comprehensive benchmark comprising 70,448 samples augmented by GPT-4. This benchmark simulates diverse real-world attack vectors that circumvent conventional defenses in the MCP paradigm, thereby laying a solid foundation for future research on securing LLM-tool ecosystems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Defense Mechanism Coverage Analysis on 23 Attack Vectors across 7 Threat Categories](<https://www.sota2.com/research/sota/defense-mechanism-coverage-analysis-on-23-attack-vectors-across-7-threat-categories.md>): Defense Mechanism Coverage Analysis; 23 Attack Vectors across 7 Threat Categories; Overall Coverage: 30.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.10991>)

[PDF](<https://arxiv.org/pdf/2508.10991.pdf>)
