MCPLow riskUnclaimed

shellward

AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.

jnMetaCodejnmetacode/shellward★ 140Updated Mar 23, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.jnMetaCode/shellward",
  "description": "AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.",
  "repository": {
    "url": "https://github.com/jnMetaCode/shellward",
    "source": "github"
  },
  "version": "0.5.11",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "shellward",
      "version": "0.5.11",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Security mode: enforce (block + log) or audit (log only)",
          "format": "string",
          "name": "SHELLWARD_MODE"
        },
        {
          "description": "Locale: auto, zh, or en",
          "format": "string",
          "name": "SHELLWARD_LOCALE"
        },
        {
          "description": "Injection detection threshold 0-100 (lower = stricter)",
          "format": "string",
          "name": "SHELLWARD_THRESHOLD"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:shellward@0.5.11
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. #10.5.11latestOct 7, 2026