Skip to content
Search
paperMay 2026Unreviewed

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

Sultan Zavrak

View resourcePDF

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

Monitoring & Detection

Cite

@misc{zavrak2026mcpshield,
  title = {{MCPShield: Content-Aware Attack Detection for LLM Agent Tool-Call Traffic}},
  author = {Sultan Zavrak},
  year = {2026},
  month = may,
  eprint = {2605.11053},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.11053}
}