cost-anomaly
AI agents call cost-anomaly 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 indicates cost analysis/monitoring, which typically retrieves and analyzes billing data without modifying it. However, confidence is moderate (0.65) because the description is empty and 'anomaly' could theoretically trigger automated responses depending on implementation. In the absence of clarification, the most reasonable interpretation is that this is a Read operation for cost monitoring/analysis.
From the tool's definition Tool name 'cost-anomaly' suggests analysis or detection of cost anomalies in AWS SageMaker, which would be a querying/retrieval operation rather than a data-modifying or destructive action.
Attacks that exploit this kind of access
cost-anomaly. 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 cost-anomaly: 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.
cost-anomaly 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 cost-anomaly 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 cost-anomaly. 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.
cost-anomaly 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.