AI agents call wazuh_query_vulnerabilities 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.
Despite the empty description, the tool name strongly suggests a read-only query operation that fetches vulnerability information. No modification, deletion, execution, or financial operations are implied. Confidence is slightly reduced due to missing description, but the naming pattern and server context provide sufficient evidence for Read classification.
From the tool's definition Tool name 'wazuh_query_vulnerabilities' indicates a query operation that retrieves vulnerability data from the Wazuh SIEM/XDR platform.
Attacks that exploit this kind of access
wazuh_query_vulnerabilities. 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_query_vulnerabilities: 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_query_vulnerabilities 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_query_vulnerabilities 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_query_vulnerabilities. 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_query_vulnerabilities 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 →