list_agent_runtimes
AI agents call list_agent_runtimes 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.
List operations retrieve data without side effects. No description is provided, which reduces confidence slightly, but the verb 'list' in the tool name is a clear indicator of a Read category tool. Listing agent runtimes would query SageMaker's agent runtime configurations and return results without altering state.
From the tool's definition Tool name 'list_agent_runtimes' contains 'list', which is a read operation pattern. The description is empty, limiting confidence, but the naming convention strongly suggests querying available agent runtimes without modification.
Attacks that exploit this kind of access
list_agent_runtimes. 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 list_agent_runtimes: 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.
list_agent_runtimes 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 list_agent_runtimes 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 list_agent_runtimes. 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.
list_agent_runtimes 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.