English Français العربية

Infraveil Agent Guard

Official registry AI and agents

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

Source code Website

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

PYPI package infraveil-guard
Claude Code 
claude mcp add infraveil-agent-guard -e 'INFRAVEIL_GUARD_THRESHOLD=<INFRAVEIL_GUARD_THRESHOLD>' -e 'INFRAVEIL_GUARD_MODE=<INFRAVEIL_GUARD_MODE>' -e 'INFRAVEIL_GUARD_HOME=<INFRAVEIL_GUARD_HOME>' -- uvx infraveil-guard==0.1.1
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "infraveil-agent-guard": {
            "command": "uvx",
            "args": [
                "infraveil-guard==0.1.1"
            ],
            "env": {
                "INFRAVEIL_GUARD_THRESHOLD": "<INFRAVEIL_GUARD_THRESHOLD>",
                "INFRAVEIL_GUARD_MODE": "<INFRAVEIL_GUARD_MODE>",
                "INFRAVEIL_GUARD_HOME": "<INFRAVEIL_GUARD_HOME>"
            }
        }
    }
}

Environment variables

  • INFRAVEIL_GUARD_THRESHOLD Severity at/above which an action is gated: none|low|medium|high|critical (default high).
  • INFRAVEIL_GUARD_MODE enforce (block dangerous actions pending approval) or audit (log only, never block). Default enforce.
  • INFRAVEIL_GUARD_HOME Directory for the ledger and approval queue (default ~/.infraveil-guard).

Frequently asked questions

What is Infraveil Agent Guard?

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

How do I install Infraveil Agent Guard?

It runs on your machine. In Claude Code: claude mcp add infraveil-agent-guard -e 'INFRAVEIL_GUARD_THRESHOLD=<INFRAVEIL_GUARD_THRESHOLD>' -e 'INFRAVEIL_GUARD_MODE=<INFRAVEIL_GUARD_MODE>' -e 'INFRAVEIL_GUARD_HOME=<INFRAVEIL_GUARD_HOME>' -- uvx infraveil-guard==0.1.1. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Infraveil Agent Guard need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Infraveil Agent Guard open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains Infraveil Agent Guard?

It is published by infraveilhq. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.