mcp-deadbugz-simulator
MCP Deadbugz Simulator
2026년 8월 Pillar Security가 발견한 Deadbugz MCP 공급망 공격의 로컬 시뮬레이션입니다.
이 저장소에 포함된 내용
3-콜 게이트 우회 기법을 사용하는 악성 MCP 서버 공격이 실제로 동작함을 입증하는 Python 테스트 하네스 로컬 LLM을 사용한 선택적 에이전트 시뮬레이션
Related MCP server: MCP Decoy Server
공격 패턴
서버가 처음 3번의 호출 동안 정상적인 도구를 표시
4번째 호출이 tools/listChanged 알림을 트리거
도구 설명이 자격 증명 탈취 지침으로 변형
AI 에이전트가 악성 지침을 따름
요구 사항
Python 3.10+ MCP SDK
사용 방법
git clone https://github.com/anexbin/mcp-deadbugz-simulator.git cd mcp-deadbugz-simulator pip install -r requirements.txt python server/malicious_server.py python client/test_harness.py
파일
server/malicious_server.py - 공격 서버 client/test_harness.py - 개념 증명 agent/local_agent.py - 선택적 LLM 통합 configs/ - 예시 MCP 구성
면책 조항
교육 및 연구 목적으로만 사용하십시오.
참고 자료
https://www.pillar.security/blog/deadbugz-currently-active-mcp-supply-chain-campaign https://modelcontextprotocol.io
라이선스
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Research honeypot. Logs connections and tool arguments; injects instructions. Read README first.
Security research: MCP registries verify identity, not tool behavior. See gtfo.dev.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Related MCP Servers
- FlicenseDqualityNot gradedmaintenanceA proof-of-concept attack that exploits Model Context Protocol (MCP) tool registration to achieve persistent agent poisoning in AI assistants like Cursor, embedding malicious instructions that persist across chat contexts without requiring tool execution.2-
- AlicenseNot gradedqualityCmaintenanceA deception-based threat detection server that impersonates enterprise MCP integrations to log and forward attacker interactions to SIEM systems. It provides convincing fake responses across 38 tools while capturing forensic details of all MCP tool calls.MIT
- AlicenseCqualityDmaintenanceAn educational MCP server exposing shell command execution (PowerShell and sh) and a benign tool for learning about MCP tools, resources, and security risks like tool poisoning.33MIT
- AlicenseNot gradedqualityBmaintenanceEnables defenders to deploy a decoy MCP tool server that records and fingerprints how LLM agents probe, escalate, and persist, without exposing real systems.MIT