AI agents call wazuh_search_events 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 retrieves security event data from Wazuh for analysis purposes. 'Search' and 'events' are characteristic of read operations with no side effects. The primary risk is information disclosure if an AI agent queries sensitive security events or logs without proper context filtering, hence medium severity.
From the tool's definition Tool name 'wazuh_search_events' indicates a search/query operation. Server context describes 'query Wazuh SIEM/XDR for alert triage, threat hunting, compliance audits, and incident response.' Sibling tools like 'wazuh_alert_summary', 'wazuh_get_alert', and…
Attacks that exploit this kind of access
wazuh_search_events. 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_search_events: 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_search_events 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_search_events 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_search_events. 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_search_events 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 →