AI agents call get_manager_config 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 configuration data from the Wazuh manager without modifying, deleting, or executing any operations. It is purely informational, making it a Read category tool with low severity. While configuration details could be sensitive, exposure is limited to viewing existing settings rather than enabling unauthorized changes or system-level actions.
From the tool's definition Tool name 'get_manager_config' and description 'Get the active Wazuh manager configuration for a specific section' indicate a retrieval operation with no modification or execution of commands.
Attacks that exploit this kind of access
Get the active Wazuh manager configuration for a specific section. 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_manager_config: 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_manager_config 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_manager_config 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_manager_config. 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_manager_config 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 →