Auditable, token-gated DeepSeek Harness remote gateway: mobile QR access, per-device sessions, Host/Origin rewrite, settings/credentials/directory support.

SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments, security roadmaps, and compliance checklists. Installs on Claude Code, Codex, ChatGPT, Antigravity, and any SKILL.md-compatible agent.

CLI tool to block --no-verify flag in git commands. Prevents AI agents from bypassing git hooks.

Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.

Fail-closed LLM-assisted approval reviewer for DeepSeek Harness

Deterministic Runtime Execution Governance & Security Circuit-Breaker for DSH & Multi-Agent Workstations

General-purpose MCP connector, connection manager, plugin extension, and integration marketplace for DeepSeek Harness, initiated and maintained by Qichacha/QCC.

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.

Probe any ACP-compatible agent for its capabilities (models, modes, configOptions, prompt capabilities, auth methods, MCP transports). No real prompt required; no token cost.

Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.

AI-powered whitebox penetration testing plugin for Claude Code. 9 languages, 22 skills, 7 autonomous agents. STRIDE threat modeling, OWASP 2025 coverage, polyglot monorepo support.

Claude Code plugin that analyzes your project, asks 3 questions, and generates a complete payment integration (Stripe · Mercado Pago · Wompi · Lemon Squeezy + frontend + DB + signed webhook + customer portal + refund). Local-first, security-enforced via PostToolUse hooks. Bilingual ES/EN.

AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools, and vulnerable code.

Official SonarQube MCP Server for code quality and security in AI agents

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

CVE hunting harness for Claude Code - 20 skills, 5-agent team, systematic vulnerability research with false positive elimination

MCP server for JADX-AI Plugin

Enables AI agents to perform passive security scans on domains, checking email spoofing (DMARC/SPF/DKIM), TLS weaknesses, security headers, exposed files, and subdomain-takeover risk without needing an API key.

The agent harness for offsec. It's a plugin for Claude Code packed with skills, hooks, memory system that works best for using Claude Code to achieve autonomous pentest/ctf

lunar.dev: Agent native MCP Gateway for governance and security

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.

🦾 MONSTER ENGINEER v2 - Ultimate AI CLI with 63 Skills, 12 Superpowers, 14 Agents. Multi-Agent Orchestration, Cost-Aware, Security Scorecard, Parallel-First.

MCP configuration to connect AI agent to a Linux machine.

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!