Get the key of an agent.
AI agents call get_agent_key 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.
This tool retrieves sensitive agent keys used for authentication and secure communication in Wazuh. While it performs a Read operation (no data modification), the severity is elevated to 'high' because agent keys are cryptographic credentials that could be misused to impersonate agents or compromise the security infrastructure if exposed to an unauthorized AI agent.
From the tool's definition Tool name 'get_agent_key' and description 'Get the key of an agent' indicate retrieval of agent authentication credentials/keys without modification or deletion.
Attacks that exploit this kind of access
Get the key of an agent. 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 get_agent_key: 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.
get_agent_key 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_agent_key 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_agent_key. 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_agent_key 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 →