mcpx
Verified Safeby rossja
Overview
This project provides an adversarial MCP server for AI red-teaming and safety evaluation of AI tool integrations.
Installation
No command providedSecurity Notes
The project is designed for adversarial testing, explicitly defining its defensive scope. It implements robust security features including HTTPS, OAuth 2.0 with PKCE, JWT tokens with expiration/refresh, bcrypt password hashing, CSRF protection, modern TLS, security headers, and input validation. API keys are managed via environment variables. The primary 'risk' is inherent to its purpose (testing adversarial scenarios), not internal security flaws, assuming proper deployment in a controlled environment as documented.
Similar Servers
mcp-scanner
A Python tool for scanning Model Context Protocol (MCP) servers and tools to detect potential security findings by leveraging Cisco AI Defense API, YARA rules, and LLM-as-a-judge.
mcp-server-code-execution-mode
This server enables LLM agents to execute Python code in a highly secure, isolated container environment, facilitating complex multi-tool orchestration and data analysis with minimal LLM context token usage.
mcp-interviewer
A Python CLI tool designed to evaluate, test, and generate reports on Model Context Protocol (MCP) servers to ensure compatibility and quality for LLM agent use cases.
zeromcp
A minimal, pure Python Model Context Protocol (MCP) server for exposing tools, resources, and prompts via HTTP/SSE and Stdio transports.