MCP Poisoning Attack - PoC
This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.
Directory
This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.
Enables seamless deployment of containerized applications directly from code editors through a three-step workflow of GitHub authentication, repository setup…
Integrates with Azure DevOps to enable querying work items, creating tasks, searching code repositories, and retrieving project information without context…
AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.
Provides a bridge to GitHub Gists for creating, retrieving, updating, listing, and deleting code snippets directly through conversational interfaces.
Enable AI agents to secure code with [Semgrep](https://semgrep.dev/).
Arcjet is the runtime security platform that ships with your AI code.
Manage OPNsense firewalls using Infrastructure as Code (IaC) principles.
Provides direct access to GitHub and GitLab repositories for code exploration, searching, and analysis with intelligent file filtering and support for various…
Curated by Archimedes Market. Static security analysis exposed as MCP tools. OWASP top 10, secrets detection, custom rule packs. Baseline scanning focuses on…
Store and retrieve API keys and secrets locally for Claude Code. No cloud services, no .env files scattered across projects. Secrets are stored in a SQLite…
The only MCP server that gates skill installation behind a full security scan. 60+ threat patterns, 13 MCP tools, and support for 7 clients including Claude…
AI-Powered Security Analysis for AWS — official MCP server. Analyze IAM policies and CloudFormation templates from any MCP client.
Connect real-time cybersecurity threat intelligence to your AI workflows through standardized tools and resources. Access comprehensive IOCs, CVEs, TTPs, and…
A Model Context Protocol (MCP) server for scanning IP addresses for vulnerabilities. This server provides tools to perform security scanning on individual IPs…
Wasm sandbox runtime for AI agent code execution. Executes JavaScript, regex, JMESPath, and SQL inside fuel-metered WebAssembly cartridges. Infinite loops trap…
Real security scanners for AI coding agents: SAST (441 rules), secret detection (419+ patterns), dependency CVEs, MCP/skill vetting, MITRE ATT&CK. Real…
EU AI Act compliance in your editor. Classify risk, cite obligations, draft Article 50 disclosures.
Security scanner for AI agents, MCP servers and agent skills.
A secure bridge for LLMs to safely execute command-line tools via the Model Context Protocol (MCP).
Connects AI to WhatsApp accounts using TypeScript and Baileys, enabling message history retrieval, contact search, and secure communication through local…
Tellix is a conversational recon interface powered by httpx and LLMs. Just ask.
Secure, self-hostable sandbox for running Python, TypeScript, and Bash code in isolated Docker containers with automatic resource management for local command…
Enables reverse engineering of binary files through IDA Pro's headless mode, providing tools for function analysis, disassembly, decompilation, and code…