MCP Server MCP

Infraveil Agent Guard

By github 👁 1 views ▲ 0 votes

Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.

Homepage Verified source GitHub

Install

uvx infraveil-guard

Configuration Example

{
  "remotes": [],
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "infraveil-guard",
      "version": "0.1.1",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Severity at/above which an action is gated: none|low|medium|high|critical (default high).",
          "name": "INFRAVEIL_GUARD_THRESHOLD"
        },
        {
          "description": "enforce (block dangerous actions pending approval) or audit (log only, never block). Default enforce.",
          "name": "INFRAVEIL_GUARD_MODE"
        },
        {
          "description": "Directory for the ledger and approval queue (default ~/.infraveil-guard).",
          "name": "INFRAVEIL_GUARD_HOME"
        }
      ]
    }
  ]
}

mcp model-context-protocol pypi