ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

arXiv:2607.19432 · cs.CR, cs.AI · Submitted 2026-07-20 · Read on arXiv

Om Narayan, Rashmi Jyoti, Ramkinker Singh

cs.CR, cs.AI

Submitted: 2026-07-20

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Model Context Protocol — 9× in this paper
• Trace — 9× in this paper · explained in 2 episodes
• Feature Extraction — 6× in this paper · explained in 2 episodes
• Direct Sequential Attack — 4× in this paper
• Hidden Markov Model — 4× in this paper
• AI Agents — 3× in this paper · explained in 2 episodes
• Analyzer — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Data Flow — 3× in this paper
• Indirect Injection Chain — 3× in this paper
• Hybrid Multi-Stage Attack — 2× in this paper
• Output Characteristics — 2× in this paper
• Parameter Sensitivity — 2× in this paper
• Provenance — 2× in this paper · explained in 4 episodes
• Tool Category — 2× in this paper
• Agentic AI — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Model Context Protocol (MCP) — 1× in this paper · explained in 8 episodes

Sources

• Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
• STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
• The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism
• MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
• MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI
• MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning
• Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem
• MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
• MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers
• Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies
• Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs