Returns basic information about the health of the cluster.
AI agents call get_cluster_health to retrieve information from Elasticsearch/OpenSearch MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves cluster health status information without modifying any data or executing operations. It is a passive monitoring/diagnostic action that falls squarely within the Read category. The severity is low because cluster health information is non-sensitive operational metadata and misuse poses minimal risk.
From the tool's definition Tool name is 'get_cluster_health' and description states it 'Returns basic information about the health of the cluster.' The verb 'Returns' and action of retrieving health metrics indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Returns basic information about the health of the cluster. It is categorised as a Read tool in the Elasticsearch/OpenSearch MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Elasticsearch/OpenSearch MCP Server MCP server in PolicyLayer and add a rule for get_cluster_health: 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 Elasticsearch/OpenSearch MCP Server. Nothing to install.
get_cluster_health 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_health 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_health. 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_health is provided by the Elasticsearch/OpenSearch MCP Server MCP server (rbedoyag/elasticsearch-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 →