AI agents call search_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.
The tool performs read-only queries against a vulnerability database. Searching and retrieving vulnerability information has no side effects, cannot execute code, and does not modify or delete data. While vulnerability information could be sensitive, the risk is in the data itself rather than the tool's function. This is a straightforward data retrieval operation with low blast radius if misused by an agent.
From the tool's definition Tool name is 'search_vulnerabilities' and description states it 'Search[es] Wazuh vulnerability inventory' — this is a query/search operation that retrieves vulnerability data without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Search Wazuh vulnerability inventory by CVE, package, agent, or description. 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 search_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.
search_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 search_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 search_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.
search_vulnerabilities is provided by the Wazuh MCP server (solomonneas/wazuh-mcp). 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 →