policy_list
AI agents call policy_list 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.
The suffix 'list' strongly suggests a read-only query operation that retrieves existing policies without modification. No verbs like delete, create, update, or execute appear. The empty description reduces confidence slightly, but the naming convention is a reliable signal for a benign read operation. Blast radius is minimal—listing policies may expose metadata but permits no harmful actions.
From the tool's definition Tool name 'policy_list' indicates a listing operation (list). Description is empty, limiting specificity.
Attacks that exploit this kind of access
policy_list. 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 policy_list: 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.
policy_list 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 policy_list 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 policy_list. 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.
policy_list 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.