AI Agent Security Audit

Overview

AI Agent Security Audit is an MCP server that performs red-team probes and missing-guardrail reviews on AI agents, then suggests fixes. Any MCP-compatible AI assistant can call its tools directly during conversations or agent runs, letting the model decide when security testing is needed.

The server runs remotely at https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit with no local installation required. It requires no authentication. The latest release is v1.1.0. Learn more at https://llmrt-companion.manhliemcn4euwlu.workers.dev/agent.

AI Agent Security Audit appears in the AI & Agents category on mcp.site and integrates with all major MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim this listing to verify ownership and keep information up to date.

Installation

Settings → Connectors → Add custom connector
Name: AI Agent Security Audit
URL:  https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit