AI agents call get_agent_stats to retrieve information from Wazuh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves system performance metrics from a Wazuh agent without creating, modifying, deleting, or executing any operations. It is a read-only information retrieval operation with minimal risk—the returned data is informational only and cannot be weaponized for lateral movement or data exfiltration in isolation. Severity is low due to limited blast radius.
From the tool's definition Tool name 'get_agent_stats' and description 'Get system statistics (CPU, memory, disk) for a specific Wazuh agent' indicate retrieval of monitoring data with no modification or execution capabilities.
Attacks that exploit this kind of access
Get system statistics (CPU, memory, disk) for a specific Wazuh agent. It is categorised as a Read tool in the Wazuh MCP Server, which means it retrieves data without modifying state.
Register the Wazuh MCP server in PolicyLayer and add a rule for get_agent_stats: 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.
get_agent_stats is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_agent_stats 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.
Set action: deny in the PolicyLayer policy for get_agent_stats. 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.
get_agent_stats is provided by the Wazuh MCP server (solomonneas/wazuh-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →