agent-security-scanner-mcp

About agent-security-scanner-mcp

Use agent-security-scanner-mcp with your agent

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

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

Frequently asked questions

What is agent-security-scanner-mcp?

agent-security-scanner-mcp is an MCP (Model Context Protocol) server by sinewaveai in the Security category. Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

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

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

Yes — the source code is public at github.com/sinewaveai/agent-security-scanner-mcp, with 110 GitHub stars.

Can AI agents pay to use agent-security-scanner-mcp?

Not yet through Loomal — agent-security-scanner-mcp 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.