j3ssie/osmedeus
Osmedeus is a powerful and modern orchestration engine designed for reconnaissance and penetration testing workflows, written in Go.
Awesome AI Agents › Red-Teaming Platforms
lasso-security/mcp-gateway
MCP Gateway is a sophisticated plugin-based gateway designed to orchestrate multiple Model Context Protocol (MCP) servers, providing a centralized and enhanced AI infrastructure. It acts as an intermediary between large language models (LLMs) and various MCP servers, managing server configurations, lifecycle, and request/response interception to sanitize sensitive information such as tokens and credentials. The gateway reads configurations from a `mcp.json` file and supports adding multiple MCP servers under its management, offering a unified interface for discovering and interacting with these proxied MCPs. Installation is straightforward, with a recommended Python package available via pip, and the gateway can be run with specified plugins to enable features like token masking and tracing. It supports Docker deployment with options to include additional dependencies for certain plugins. The gateway automatically masks sensitive tokens in responses to prevent credential exposure while maintaining functionality. MCP Gateway includes tools like `get_metadata` for providing information about available MCPs and `run_tool` for executing capabilities from proxied MCPs after sanitization. It supports a plugin system with built-in guardrails to enhance security and functionality, including plugins for PII masking, token/secret masking, custom policies, prompt injection prevention, and harmful content filtering. The basic plugin masks common secrets such as Azure client secrets, GitHub tokens, AWS access tokens, JWT tokens, and more. The presidio plugin integrates Microsoft Presidio for identifying and anonymizing sensitive data like credit cards, IP addresses, emails, and phone numbers. The lasso plugin offers advanced AI safety guardrails, requiring an API key from Lasso Security. Overall, MCP Gateway is a powerful tool for enterprises looking to securely manage and extend their AI model context infrastructure with robust security features and plugin extensibility.
https://github.com/lasso-security/mcp-gateway
Also in Red-Teaming Platforms
Tencent/AI-Infra-Guard
AI-Infra-Guard by Tencent is a comprehensive AI Red Teaming platform offering intelligent vulnerability scanning, MCP server risk detection, and jailbreak evaluation to enhance AI security.
beclab/Olares
Olares is an open-source sovereign cloud operating system that enables users to run local AI models, manage personal data, and self-host various applications securely and privately on their own hardware.
GH05TCREW/pentestagent
Python terminal agent for AI-assisted penetration testing that drives nmap, sqlmap, a browser and MCP servers, with assist, autonomous agent, multi-agent crew and guided interactive modes.
larlarua/AutoCVE
Agent-driven platform that automates CVE discovery end to end, using multiple coordinated agents to audit source code, verify vulnerabilities, and generate submission-ready reports.
SanMuzZzZz/LuaN1aoAgent
LuaN1aoAgent v2 is an autonomous security research agent that splits work between Planner, Executor and Observer roles and records every conclusion as evidence-backed nodes in a causal reasoning graph.
qualifire-dev/rogue
Client-server platform for evaluating and red-teaming AI agents over A2A, MCP or direct Python calls, with 75+ vulnerabilities, 20 attack techniques and compliance-framework reporting.
ASCIT31/Dark-Moon
Open-source autonomous penetration testing platform where specialised agents plan and run real offensive operations through a controlled MCP execution layer, with local tokenization that hides sensitive values from the model.