get_cloudwatch_metrics
AI agents call get_cloudwatch_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 'get_' prefix indicates a retrieval operation. CloudWatch metrics are time-series data points used for monitoring; fetching them has no side effects. However, severity is medium rather than low because CloudWatch metrics may reveal sensitive operational details (resource utilization, performance patterns, error rates) that could inform an attacker about system architecture or vulnerabilities.
From the tool's definition Tool name is 'get_cloudwatch_metrics', which follows the read-pattern verb 'get'. CloudWatch metrics retrieval is a read operation that queries monitoring data without modifying system state.
Attacks that exploit this kind of access
get_cloudwatch_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_cloudwatch_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_cloudwatch_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_cloudwatch_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_cloudwatch_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_cloudwatch_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.