get_cat_shards
AI agents call get_cat_shards 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.
The 'get_' prefix and sibling context strongly indicate a read-only retrieval operation. The Elasticsearch CAT shards endpoint returns cluster state information without side effects. Confidence is 0.7 rather than higher because the description is empty, creating minor uncertainty about the exact implementation and scope of what metadata might be exposed.
From the tool's definition Tool name 'get_cat_shards' follows the pattern of sibling 'get_' tools on this Wazuh server which are retrieval-only (e.g., get_agent_component_stats, get_agent_hardware, get_agent_netaddr).
Attacks that exploit this kind of access
get_cat_shards. 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_cat_shards: 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_cat_shards 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_cat_shards 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_cat_shards. 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_cat_shards 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 →