pith. sign in

From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

4 Pith papers cite this work. Polarity classification is still indexing.

4 Pith papers citing it
abstract

The model context protocol (MCP) standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify attacks by their observable effects, obscuring how attacks behave across different MCP server components and overlooking multi-component attack chains. Meanwhile, existing defenses are less effective when facing multi-component attacks or previously unknown malicious behaviors. This work presents a component-centric perspective for understanding and detecting malicious MCP servers. First, we build the first component-centric PoC dataset of 114 malicious MCP servers where attacks are achieved as manipulation over MCP components and their compositions. We evaluate these attacks' effectiveness across two MCP hosts and five LLMs, and uncover that (1) component position shapes attack success rate; and (2) multi-component compositions often outperform single-component attacks by distributing malicious logic. Second, we propose and implement Connor, a two-stage behavioral deviation detector for malicious MCP servers. It first performs pre-execution analysis to detect malicious shell commands and extract each tool's function intent, and then conducts step-wise in-execution analysis to trace each tool's behavioral trajectories and detect deviations from its function intent. Evaluation on our curated dataset indicates that Connor achieves an F1-score of 94.6%, outperforming the state of the art by 8.9% to 59.6%. In real-world detection, Connor identifies two malicious servers.

citation-role summary

background 1

citation-polarity summary

fields

cs.CR 3 cs.SE 1

years

2026 4

verdicts

UNVERDICTED 4

roles

background 1

polarities

background 1

clear filters

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Behavioral Integrity Verification for AI Agent Skills cs.CR · 2026-05-12 · unverdicted · none · ref 19 · internal anchor

    BIV audits AI agent skills at scale, finding 80% deviate from declared behavior on 49,943 skills and achieving 0.946 F1 for malicious skill detection.