Security-enhanced MCP proxy. Proxies all plugin MCP servers through a unified security layer. Block destructive tool calls, audit operations, and recover configs with /armour commands.
Security proxy for MCP servers that intercepts and blocks dangerous tool calls from AI coding assistants, providing audit logging and configurable policies.
Why this plugin
Acts as a firewall for AI agents, preventing destructive commands like 'rm -rf' and unsafe script execution before they run, unlike alternatives that lack real-time blocking. Solves the problem of AI assistants accidentally executing harmful operations.
Prerequisites
Claude Code or compatible AI coding assistant. Requires installation via provided script or manual plugin setup. No explicit API keys needed.
/plugin marketplace add fuushyn/armour/plugin install armour@armour-marketplaceCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation