MCPLow riskUnclaimed

arc-security

Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.

arcself.comarcself.com/arc-securityUpdated Feb 17, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "com.arcself/arc-security",
  "description": "Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.",
  "repository": {
    "url": "https://github.com/ArcSelf/arc-security-mcp",
    "source": "github"
  },
  "version": "0.5.1",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "arc-security-mcp",
      "version": "0.5.1",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:arc-security-mcp@0.5.1
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. #10.5.1latestOct 7, 2026