agent-security

About agent-security

Use agent-security with your agent

claude mcp add agent-security -- npx -y agent-security-mcp

{
  "mcpServers": {
    "agent-security": {
      "command": "npx",
      "args": [
        "-y",
        "agent-security-mcp"
      ]
    }
  }
}

Frequently asked questions

What is agent-security?

agent-security is an MCP (Model Context Protocol) server by mdfifty50-boop in the Security category. Security scanning and threat detection for AI agents

How do I connect agent-security to Claude, Cursor, or another MCP client?

Install agent-security from its npm package (agent-security-mcp) 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 open source?

Yes — the source code is public at github.com/mdfifty50-boop/agent-security-mcp.

Can AI agents pay to use agent-security?

Not yet through Loomal — agent-security 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.