Security & Testing MCP 服务器

Playwright

Automates browsers and APIs using the Playwright Model Context Protocol, enabling LLMs to interact with web pages.

AgentNull

Provides a catalog of AI agent attack vectors and proof-of-concept exploits.

Playwright

Provides comprehensive browser automation capabilities for AI assistants using Playwright.

Plugged.in Random Number Generator

Provides cryptographically secure random number generation for AI applications, LLMs, and other systems requiring high-quality randomness.

Claude ARM64 Browser

Enables ARM64 browser automation for AI-driven SaaS testing on budget hardware, overcoming limitations of traditional tools like Playwright and Puppeteer.

Micro

Facilitates the composition of multiple single-purpose Model Context Protocol (MCP) servers into a secure, observable, and independently deployable context mesh for LLMs and agents.

Kali Penetration Test

Integrates Kali Linux security tools with AI assistants for ethical penetration testing in a controlled Docker environment.

Hybrid AI

Creates a transparent, inspectable decision layer using McCulloch-Pitts neurons to bridge the 'black box' problem of neural networks for safety-critical and regulated AI.

Modular Server

Serves as a config-driven, modular Model Context Protocol server enabling the execution of various plugins and tools.

Debug

Provides breakpoint-based Python debugging capabilities via API and CLI, designed for integration with AI assistants and development tools.

AIDomesticCoreAIJ

Establishes a foundational AI kernel to serve as the execution, reasoning, orchestration, and governance core for domestic, enterprise, and sovereign AI systems.

Contree

Provides secure, sandboxed cloud container environments for AI agents to execute code with full root access, networking, and persistent images.

Axe

Integrates accessibility testing and AI-powered remediation directly into IDEs, enabling AI coding agents to find and fix web accessibility issues without disrupting development workflows.

Defense

Provides AI assistants access to 94 defensive security tools on Linux, enabling system hardening, compliance, and incident response via natural language.

Authensor

Provides an open-source safety stack for AI agents, encompassing policy enforcement, content scanning, approval workflows, and cryptographic audit trails.

Sekretlink

Integrates with sekret.link to create encrypted, self-destructing secret links for secure sharing.

ArtSleuth

Performs AI-powered art forensics and analysis, including brushstroke examination, style attribution, forgery detection, and interpretable visual explanations.

Claudecode Security Ops Guard

Provides an essential enforcement layer for Claude Code, preventing dangerous operations, defending against prompt injection, and automating security and operational tasks.

Pop Pay

Provides a runtime security layer for AI agent commerce, isolating payment credentials to prevent hallucination-induced financial risks.

Memento

Equips AI agents with an autonomous nervous system for local memory management, active code coercion, and robust goal alignment.