Get cluster statistics
AI agents call get_cluster_stats to retrieve information from mcp-OpenSearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves cluster statistics from OpenSearch without modifying or executing anything. It is a straightforward read operation with no side effects. The blast radius of misuse is minimal—an agent could only learn about cluster state, not alter it or trigger actions.
From the tool's definition Tool name 'get_cluster_stats' and description 'Get cluster statistics' indicate a retrieval operation. Server description lists this under 'Cluster Management Tools' alongside 'Get cluster health status', both clearly read-only queries.
Attacks that exploit this kind of access
Get cluster statistics. It is categorised as a Read tool in the mcp-OpenSearch MCP Server, which means it retrieves data without modifying state.
Register the mcp-OpenSearch MCP server in PolicyLayer and add a rule for get_cluster_stats: 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 mcp-OpenSearch. Nothing to install.
get_cluster_stats 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_cluster_stats 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_cluster_stats. 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_cluster_stats is provided by the mcp-OpenSearch MCP server (showjason/opensearch-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 →