MCPLow riskUnclaimed

guardianshield

AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs

sparkvibe-iosparkvibe-io/guardianshield★ 3Updated Mar 3, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.sparkvibe-io/GuardianShield",
  "description": "AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs",
  "repository": {
    "url": "https://github.com/sparkvibe-io/GuardianShield",
    "source": "github"
  },
  "version": "1.2.1",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "guardianshield",
      "version": "1.2.1",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Default safety profile (general, education, healthcare, finance, children)",
          "format": "string",
          "name": "GUARDIANSHIELD_PROFILE"
        },
        {
          "description": "Path to the SQLite audit database",
          "format": "string",
          "name": "GUARDIANSHIELD_AUDIT_PATH"
        },
        {
          "description": "Set to 1 for debug logging",
          "format": "string",
          "name": "GUARDIANSHIELD_DEBUG"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:guardianshield@1.2.1
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. #11.2.1latestOct 7, 2026