A
licenseNot graded
qualityB
maintenanceEnables 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
mcp-deadbugz-simulator
by ahmedaens
MCP Deadbugz Simulator
Локальная симуляция атаки на цепочку поставок Deadbugz MCP, обнаруженной Pillar Security в августе 2026 года.
Что содержит этот репозиторий
Вредоносный MCP-сервер с техникой обхода шлюза за 3 вызова Python-тестовый стенд для доказательства работоспособности атаки Опциональная симуляция агента с локальной LLM
Related MCP server: Command-Injection-MCP
Схема атаки
Сервер показывает безвредные инструменты в течение первых 3 вызовов
4-й вызов запускает уведомление tools/listChanged
Описания инструментов мутируют в инструкции по краже учётных данных
ИИ-агент следует вредоносным инструкциям
Требования
Python 3.10+ MCP SDK
Использование
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
Файлы
server/malicious_server.py — сервер атаки client/test_harness.py — доказательство концепции agent/local_agent.py — опциональная интеграция с LLM configs/ — примеры MCP-конфигураций
Отказ от ответственности
Только для образовательных и исследовательских целей.
Ссылки
https://www.pillar.security/blog/deadbugz-currently-active-mcp-supply-chain-campaign https://modelcontextprotocol.io
Лицензия
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
Maintenance
ActivityInactive
ResponsivenessNo recent community issues
Related MCP Connectors
Research decoy: fake tools, nothing is executed, every call is logged. Details on the website.
MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable
MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable
Research honeypot. Logs connections and tool arguments; injects instructions. Read README first.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceDemonstrates deceptive tool naming and unsanitized shell execution by exposing tools that perform OS fingerprinting and run local system commands through MCP. Intended for security research on vulnerabilities in the MCP ecosystem.1-
- AlicenseNot gradedqualityDmaintenancePresents 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
- AlicenseNot gradedqualityCmaintenanceServes 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