AI agents call wazuh_rules_info 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 strongly implies information retrieval rather than modification or execution. The 'wazuh_rules_info' naming pattern aligns with read-only query tools in the Wazuh ecosystem. However, confidence is moderated from 0.9 to 0.75 due to the completely empty description, which prevents direct confirmation of the tool's exact behavior and parameters.
From the tool's definition Tool name is 'wazuh_rules_info' which suggests retrieval of rules information from Wazuh; the context of sibling tools like 'wazuh_alert_summary', 'wazuh_compliance_report', 'wazuh_get_agent', and 'wazuh_get_alert' indicates this server provides…
Attacks that exploit this kind of access
wazuh_rules_info. 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_rules_info: 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_rules_info 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_rules_info 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_rules_info. 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_rules_info 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 →