AI agents call get_wazuh_version 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 version and API metadata from the Wazuh manager. It is a read-only query operation that returns information about the system without creating, modifying, executing code, deleting, or moving money. The blast radius of misuse is minimal - an attacker could only learn version information which is typically low-sensitivity metadata used for system reconnaissance.
From the tool's definition Tool name is 'get_wazuh_version' and description states 'Get the Wazuh manager version and API information' - uses 'Get' verb indicating retrieval operation with no modification or execution of external actions.
Attacks that exploit this kind of access
Get the Wazuh manager version and API information. 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 get_wazuh_version: 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.
get_wazuh_version 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 get_wazuh_version 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 get_wazuh_version. 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.
get_wazuh_version 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 →