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

arXiv: https://arxiv.org/abs/2508.10991 · HTML: https://mlsanity.com/paper/2508.10991/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 14 Aug 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 10 of 10)

- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks](https://mlsanity.com/paper/2502.13175/) (2025)
- [MPMA: Preference Manipulation Attack Against Model Context Protocol](https://mlsanity.com/paper/2505.11154/) (2025)
- [MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol](https://mlsanity.com/paper/2505.14590/) (2025)
- [MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI System](https://mlsanity.com/paper/2504.12757/) (2025)
- [We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems](https://mlsanity.com/paper/2506.13666/) (2025)
- [Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approach](https://mlsanity.com/paper/2504.19951/) (2025)
- [GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks](https://mlsanity.com/paper/2409.19521/) (2024)
- [Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs](https://mlsanity.com/paper/2508.10029/) (2025)
- [Simplified and Secure MCP Gateways for Enterprise AI Integration](https://mlsanity.com/paper/2504.19997/) (2025)

## Built on by (most cited first, 19 of 19)

- [Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents](https://mlsanity.com/paper/2509.26354/) (2025)
- [MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols](https://mlsanity.com/paper/2508.13220/) (2025)
- [TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories](https://mlsanity.com/paper/2604.07223/) (2026)
- [MCPGuard : Automatically Detecting Vulnerabilities in MCP Servers](https://mlsanity.com/paper/2510.23673/) (2025)
- [ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation](https://mlsanity.com/paper/2605.26542/) (2026)
- [SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime](https://mlsanity.com/paper/2602.19555/) (2026)
- [Trusted AI Agents in the Cloud](https://mlsanity.com/paper/2512.05951/) (2025)
- [Don't believe everything you read: Understanding and Measuring MCP Behavior under Misleading Tool Descriptions](https://mlsanity.com/paper/2602.03580/) (2026)
- [Clawed and Dangerous: Can We Trust Open Agentic Systems?](https://mlsanity.com/paper/2603.26221/) (2026)
- [A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms](https://mlsanity.com/paper/2604.05969/) (2026)
- [EVOMAL: Self-Poisoning in Self-Evolving Coding Agents](https://mlsanity.com/paper/2608.25776/) (2026)
- [MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security](https://mlsanity.com/paper/2604.07551/) (2026)
- [CASCADE: A Component Ablation and Corpus Audit of a Layered Local Defense for MCP-Based Systems](https://mlsanity.com/paper/2604.17125/) (2026)
- [ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems](https://mlsanity.com/paper/2607.19432/) (2026)
- [The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities](https://mlsanity.com/paper/2607.05743/) (2026)
- [Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation](https://mlsanity.com/paper/2608.12880/) (2026)
- [When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool Calling](https://mlsanity.com/paper/2608.17275/) (2026)
- [TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers](https://mlsanity.com/paper/2608.23763/) (2026)
- [On the Effectiveness of Kernel-Level Evidence for Agent Security](https://mlsanity.com/paper/2609.28915/) (2026)

## Abstract (arXiv)

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.