Skip to main content
Glama
Sign In
deenesjakoruzh
mcp-deadbugz-simulator

mcp-deadbugz-simulator

by ahmedaens
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

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: Command-Injection-MCP

공격 패턴

  1. 서버가 처음 3번의 호출 동안 정상적인 도구를 표시

  2. 4번째 호출이 tools/listChanged 알림을 트리거

  3. 도구 설명이 자격 증명 탈취 지침으로 변형

  4. 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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    This server cannot be deployed

    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • agent-honeypot

      alizafarbati
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables defenders to deploy a decoy MCP tool server that records and fingerprints how LLM agents probe, escalate, and persist, without exposing real systems.
      1
      MIT

    • Workspace Tools

      brian-mitchell-sec
      A
      license
      Not graded
      quality
      D
      maintenance
      Presents a plausible, tool-rich workspace surface — file reading, credential listing, command execution, database queries, and configuration retrieval — that returns only synthetic results while logging every connection, tool call, and argument received. It enables researchers to measure what MCP clients and agents actually do when handed dangerous-sounding tools, including whether they follow injected instructions or complete a retrieve-then-use credential chain.
      MIT

    • dvmcp

      ds8282
      A
      license
      Not graded
      quality
      C
      maintenance
      Serves as an intentionally vulnerable training target that exposes eight planted MCP vulnerability challenges—tool poisoning, rug pulls, path traversal, SSRF, command injection, missing auth, prompt-injection chains, and secrets exposure—each with a patched counterpart so users can exploit, detect, and remediate real-world MCP security flaws.
      Apache 2.0