Agent Security Scanner

About Agent Security Scanner

Use Agent Security Scanner with your agent

claude mcp add agent-security-scanner -- uvx agentvuln

{
  "mcpServers": {
    "agent-security-scanner": {
      "command": "uvx",
      "args": [
        "agentvuln"
      ]
    }
  }
}

Frequently asked questions

What is Agent Security Scanner?

Agent Security Scanner is an MCP (Model Context Protocol) server by mikehzp in the Security category. Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.

How do I connect Agent Security Scanner to Claude, Cursor, or another MCP client?

Install Agent Security Scanner from its pypi package (agentvuln) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.

Is Agent Security Scanner open source?

Yes — the source code is public at github.com/mikehzp/agentvuln.

Can AI agents pay to use Agent Security Scanner?

Not yet through Loomal — Agent Security Scanner is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.