AI agents call wazuh_cluster_status 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 contains 'status' which is a read-only operation. Within a SIEM context, cluster status queries are informational lookups that retrieve current state data about the Wazuh cluster (node health, connectivity, synchronization state, etc.). No capability to modify, delete, or execute operations is implied.
From the tool's definition Tool name 'wazuh_cluster_status' indicates a status query operation. No description provided, but naming pattern and server context (Wazuh SIEM/XDR for security monitoring) suggest this retrieves cluster health/state information without modification.
Attacks that exploit this kind of access
wazuh_cluster_status. 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_cluster_status: 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_cluster_status 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_cluster_status 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_cluster_status. 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_cluster_status 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 →