MCPLow riskUnclaimed

agent-security-scanner-mcp

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

sinewaveaisinewaveai/agent-security-scanner-mcp★ 122Updated Feb 6, 2026

server.json

{
  "$schema": "https://registry.modelcontextprotocol.io/v0/schema/2025-12-11",
  "name": "io.github.sinewaveai/agent-security-scanner-mcp",
  "description": "Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.",
  "repository": {
    "url": "https://github.com/sinewaveai/agent-security-scanner-mcp",
    "source": "github"
  },
  "version": "2.0.1",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "agent-security-scanner-mcp",
      "version": "2.0.1",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:agent-security-scanner-mcp@2.0.1
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #12.0.1latestOct 7, 2026