Security · Education & Learning

MCP Poisoning Poc logo

MCP Poisoning Poc

wbfoss/mcp-poisoning-poc

This research demonstrates critical security vulnerabilities in the Model Context Protocol (MCP) that allow attackers to. : GenSecAI is A non-profit community using generative AI to defend against AI-powered attacks, building open-source tools to secure our digital future from emerging AI threats.

Install

See repository

Setup steps are in the repository README.

Open README
GitHub stars
5
Author
@wbfoss
Category
Security, Education & Learning
License
MIT
Updated
Oct 6, 2026

About MCP Poisoning Poc

This research demonstrates critical security vulnerabilities in the Model Context Protocol (MCP) that allow attackers to:

GenSecAI is A non-profit community using generative AI to defend against AI-powered attacks, building open-source tools to secure our digital future from emerging AI threats.

Tools (2)

  • Organization

    GenSecAI - Generative AI Security Community

  • Website

    https://gensecai.org

Details on this page are taken from the project's README. Open README

Supported clients

Clients mentioned in this server's README:

View all
Cursor logo

Cursor

Desktop · Freemium · Proprietary

The first agentic IDE. The Cursor editor truly merges how developers and AI work together, delivering a magical coding experience.

WindowsMacOSLinux

Related MCP servers

More servers
Ida Pro MCP logo

Ida Pro MCP

mrexodia/ida-pro-mcp

1.7k

Simple MCP Server to allow vibe reversing in IDA Pro.

Security
MCP Scan logo

MCP Scan

invariantlabs-ai/mcp-scan

528

Discover and scan agent components on your machine for prompt injections and vulnerabilities (including agents, MCP servers, skills).

Security
Agentic Radar logo

Agentic Radar

splx-ai/agentic-radar

463

It allows users to create a security report for agentic systems, including.

Security
MCP Shield logo

MCP Shield

riseandignite/mcp-shield

446

MCP-Shield scans your installed MCP (Model Context Protocol) servers and detects vulnerabilities like tool poisoning attacks, exfiltration channels and cross-origin escalations.

Security
Jadx AI MCP logo

Jadx AI MCP

zinja-coder/jadx-ai-mcp

204

Fully automated MCP server + JADX plugin built to communicate with LLM through MCP to analyze Android APKs using LLMs like Claude — uncover vulnerabilities, analyze APK, and reverse engineer effortlessly.

Security
BloodHound logo

BloodHound

mordavid/bloodhound-mcp-ai

190

BloodHound-MCP is a powerful integration that brings the capabilities of Model Context Procotol (MCP) Server to BloodHound, the industry-standard tool for Active Directory security analysis. This integration allows you to analyze BloodHound data using natural language, making complex Active Directory attack path analysis accessible to everyone.

Security