MCPShield: Content-Aware Attack Detection for LLM Agent Tool-Call Traffic

Sultan Zavrak

Abstract

The Model Context Protocol (MCP) has become a widely adopted interface for LLM agents to invoke external tools, yet learned monitoring of MCP tool-call traffic remains underexplored. In this article, MCPShield is presented as an attack detection framework for MCP tool-call traffic that encodes each agent session as a graph (tool calls as nodes, sequential and data-flow links as edges), enriches nodes with sentence-embedding features over arguments and responses, and classifies sessions as benign

Categories

Cite This Resource

@article{llmsec202600071,
  title = {MCPShield: Content-Aware Attack Detection for LLM Agent Tool-Call Traffic},
  author = {Sultan Zavrak},
  year = {2026},
  url = {https://arxiv.org/abs/2605.11053},
}