Get the estimated cardinality of a HyperLogLog.
AI agents call hll_count to retrieve information from Amazon SageMaker AI 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 statistical information (cardinality estimate) from an existing HyperLogLog data structure without modifying, deleting, or executing any operations. It is purely informational and has no side effects on data or system state. The read-only nature and lack of mutability or execution capabilities place it clearly in the Read category with low severity due to minimal blast radius if misused.
From the tool's definition Tool name 'hll_count' and description 'Get the estimated cardinality of a HyperLogLog' indicate a query operation that retrieves an estimated count from a HyperLogLog data structure. The verb 'Get' explicitly describes a read operation with no side effects.
Attacks that exploit this kind of access
Get the estimated cardinality of a HyperLogLog. It is categorised as a Read tool in the Amazon SageMaker AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon SageMaker AI MCP Server MCP server in PolicyLayer and add a rule for hll_count: 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 Amazon SageMaker AI MCP Server. Nothing to install.
hll_count 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 hll_count 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 hll_count. 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.
hll_count is provided by the Amazon SageMaker AI MCP Server MCP server (awslabs.sagemaker-ai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.