Research · curated 18 Sep 2026
Securing the Tool Layer: A Threat Taxonomy and Runtime Defense Framework for Model Context Protocol Deployments
First reported aclanthology.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
MCP has become the dominant standard for connecting LLMs to external tools, and ShieldMCP's taxonomy and runtime defenses address a tool-layer attack surface that existing LLM safety measures fail to cover.
An ACL industry paper by Saurabh Yergattikar presents ShieldMCP, a runtime security framework, alongside a structured threat taxonomy for Model Context Protocol (MCP) deployments derived from 80+ attack techniques catalogued under the SAFE-MCP/OpenSSF initiative across 14 tactical categories. The work highlights that MCP introduces a new attack surface where adversaries compromise AI agents through trusted tools rather than user prompts.