AI agents call wazuh_manager_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.
The tool name 'stats' strongly suggests it retrieves status or statistics data without side effects. The absence of action verbs (create, delete, execute, modify) and the pattern of sibling stats/status/health tools all indicate this is a Read operation. Confidence is moderate (0.75) rather than high because the description is empty, preventing full verification of the tool's actual behavior.
From the tool's definition Tool name 'wazuh_manager_stats' implies retrieval of manager statistics/metrics. Sibling tools like 'wazuh_agent_health', 'wazuh_cluster_node_stats', and 'wazuh_cluster_status' establish a pattern of read-only monitoring and health queries on the Wazuh SIEM…
Attacks that exploit this kind of access
wazuh_manager_stats. 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 wazuh_manager_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.
wazuh_manager_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 wazuh_manager_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 wazuh_manager_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.
wazuh_manager_stats 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.
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 →