mcp-deadbugz-simulator
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-deadbugz-simulatorsimulate the Deadbugz 3-call attack"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Deadbugz Simulator
A local simulation of the Deadbugz MCP supply-chain attack discovered by Pillar Security in August 2026.
What this repo contains
Malicious MCP server with 3-call gate evasion technique Python test harness to prove the attack works Optional agent simulation with local LLM
Related MCP server: MCP Decoy Server
The attack pattern
Server shows benign tools for first 3 calls
4th call triggers tools/listChanged notification
Tool descriptions mutate to credential-stealing instructions
AI agent follows malicious instructions
Requirements
Python 3.10+ MCP SDK
Usage
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
Files
server/malicious_server.py - The attack server client/test_harness.py - Proof of concept agent/local_agent.py - Optional LLM integration configs/ - Example MCP configs
Disclaimer
For educational and research purposes only.
References
https://www.pillar.security/blog/deadbugz-currently-active-mcp-supply-chain-campaign https://modelcontextprotocol.io
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Security research: MCP registries verify identity, not tool behavior. See gtfo.dev.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
MEOK MCP Hardening MCP — automated security red-team for any MCP server. Maps OWASP LLM Top 10
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
- FlicenseNot gradedqualityBmaintenanceMCP server with intentionally malicious capabilities for testing Cisco AI Defense supply chain scanning.-
- AlicenseCqualityCmaintenanceAn 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