Agent Security Scanner

Overview

Agent Security Scanner is a Model Context Protocol (MCP) server: Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more. Because it speaks the Model Context Protocol, AI assistants can use Agent Security Scanner as a set of callable tools instead of you copy-pasting between apps.

It runs locally: the Python package agentvuln (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.4.2.

On mcp.site, Agent Security Scanner sits in the AI & Agents category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain Agent Security Scanner for Mikehzp, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "agent_security_scanner": {
      "command": "uvx",
      "args": [
        "agentvuln"
      ]
    }
  }
}