get_metrics
AI agents call get_metrics 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 tool name 'get_metrics' follows standard API naming conventions for read-only operations that retrieve monitoring or performance metrics. In AWS SageMaker context, this would query existing metrics without side effects. Despite the empty description lowering confidence, the tool name strongly indicates a read operation with no capability to modify, delete, or execute external code.
From the tool's definition Tool name 'get_metrics' indicates retrieval of metric data without modification. Description is empty but naming convention and position among sibling tools (which include read operations like 'ActivateAHOReadSets', 'aggregate', 'analyze_*') suggests data…
Attacks that exploit this kind of access
get_metrics. 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 get_metrics: 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.
get_metrics 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_metrics 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_metrics. 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_metrics 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.