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

mcp-deadbugz-simulator

by ahmedaens
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

MCP Deadbugz Simulator

Eine lokale Simulation des Deadbugz-MCP-Supply-Chain-Angriffs, der im August 2026 von Pillar Security entdeckt wurde.

Was dieses Repository enthält

Bösartiger MCP-Server mit 3-Call-Gate-Umgehungstechnik Python-Testrahmen zum Nachweis, dass der Angriff funktioniert Optionale Agentensimulation mit lokalem LLM

Related MCP server: Command-Injection-MCP

Das Angriffsmuster

  1. Der Server zeigt bei den ersten 3 Aufrufen harmlose Tools

  2. Der 4. Aufruf löst eine tools/listChanged-Benachrichtigung aus

  3. Tool-Beschreibungen mutieren zu Anweisungen zum Stehlen von Anmeldedaten

  4. Der KI-Agent befolgt die bösartigen Anweisungen

Anforderungen

Python 3.10+ MCP SDK

Verwendung

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

Dateien

server/malicious_server.py - Der Angriffsserver client/test_harness.py - Proof of Concept agent/local_agent.py - Optionale LLM-Integration configs/ - Beispiel-MCP-Konfigurationen

Haftungsausschluss

Nur für Bildungs- und Forschungszwecke.

Referenzen

https://www.pillar.security/blog/deadbugz-currently-active-mcp-supply-chain-campaign https://modelcontextprotocol.io

Lizenz

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
    ResponsivenessNo recent community issues

    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