PluginBench
MCP Server
Maintained
AGPL-3.0

Infraveil Agent Guard MCP Server

io.github.infraveilhq/agent-guard

What is the Infraveil Agent Guard MCP server?

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

How to install Infraveil Agent Guard

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • 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).

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "agent-guard": {
      "command": "uvx",
      "args": [
        "infraveil-guard"
      ],
      "env": {
        "INFRAVEIL_GUARD_THRESHOLD": "<YOUR_INFRAVEIL_GUARD_THRESHOLD>",
        "INFRAVEIL_GUARD_MODE": "<YOUR_INFRAVEIL_GUARD_MODE>",
        "INFRAVEIL_GUARD_HOME": "<YOUR_INFRAVEIL_GUARD_HOME>"
      }
    }
  }
}

Related MCP servers

Govern your backend control plane from your AI agent - signed, human-approval-gated.

0
Python
AGPL-3.0
View repository →

eBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging

View repository →

Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.

0
TypeScript
View repository →
EXExec Sandbox logo

Exec Sandbox

Maintained

Single exec tool running caller Python in a network-isolated locked-down sandbox.

1
Go
MIT
View repository →

Runs a command in a throwaway Kubernetes pod and returns exit code, output and artifacts.

0
Go
MIT
View repository →
SSSSH Fleet logo

SSH Fleet

Maintained

Curated ssh_probe diagnostics and single-host ssh_exec over an allowlisted SSH fleet.

0
Go
MIT
View repository →