ListAHOReferences
AI agents call ListAHOReferences 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.
Despite the empty description reducing confidence slightly, the 'List' prefix strongly suggests this is a read-only operation that retrieves or enumerates existing data without side effects. No destructive, financial, or code execution semantics are evident from the name alone. This is classified as Read with low severity due to the minimal blast radius of querying data.
From the tool's definition Tool name 'ListAHOReferences' contains the verb 'List', which typically indicates data retrieval without modification. The 'AHOReferences' likely refers to querying existing references in the AWS SageMaker context.
Attacks that exploit this kind of access
ListAHOReferences. 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 ListAHOReferences: 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.
ListAHOReferences 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 ListAHOReferences 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 ListAHOReferences. 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.
ListAHOReferences 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.