wazuh_agent_command · Wazuh MCP: Risk & Policy

WHAT IT DOES

What wazuh_agent_command does on Wazuh

AI agents invoke wazuh_agent_command to trigger actions in Wazuh. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why wazuh_agent_command needs a policy

The name 'wazuh_agent_command' strongly suggests it sends commands to Wazuh agents, which are remote endpoint actions that could trigger scripts, scans, or other operations on managed hosts. This falls under Execute. The description is empty, which lowers confidence, but in the context of a SIEM/XDR platform, agent commands typically trigger active responses or remote actions.

From the tool's definition Tool name 'wazuh_agent_command' — 'command' strongly implies executing a command on a Wazuh agent (remote endpoint).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wazuh_agent_command Rate-limited

wazuh_agent_command stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "wazuh_agent_command": {
      "limits": [
        {
          "counter": "wazuh_agent_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Wazuh, so you can run agents against it safely.

FAQ

Questions about wazuh_agent_command

What does the wazuh_agent_command tool do? +

wazuh_agent_command. It is categorised as a Execute tool in the Wazuh MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wazuh_agent_command? +

Register the Wazuh MCP server in PolicyLayer and add a rule for wazuh_agent_command: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Wazuh. Nothing to install.

What risk level is wazuh_agent_command? +

wazuh_agent_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit wazuh_agent_command? +

Yes. Add a rate_limit block to the wazuh_agent_command rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block wazuh_agent_command completely? +

Set action: deny in the PolicyLayer policy for wazuh_agent_command. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides wazuh_agent_command? +

wazuh_agent_command is provided by the Wazuh MCP server (sbharadwaj05/wazuh-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.