search_alerts
AI agents call search_alerts to retrieve information from Wazuh MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Alert search is fundamentally a read operation that retrieves existing security alert records. While the severity is marked medium rather than low because alerts contain sensitive security information that could inform an attacker about system defenses, the operation itself is non-destructive and non-modifying.
From the tool's definition Tool name 'search_alerts' indicates querying/retrieving alert data from the Wazuh security platform. No description provided, but naming convention and context within a security monitoring/analysis tool strongly suggests data retrieval without modification.
Attacks that exploit this kind of access
search_alerts. It is categorised as a Read tool in the Wazuh MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Wazuh MCP Server MCP server in PolicyLayer and add a rule for search_alerts: 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 MCP Server. Nothing to install.
search_alerts 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 search_alerts 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 search_alerts. 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.
search_alerts is provided by the Wazuh MCP Server MCP server (rayasatriatama/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 →