get_alarm_history
AI agents call get_alarm_history 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.
This tool retrieves alarm history data without side effects. While the description is empty and reduces confidence slightly, the naming convention strongly suggests a read-only operation typical of monitoring and observability features in AWS SageMaker. No create, modify, delete, or execution semantics are implied by the name.
From the tool's definition Tool name 'get_alarm_history' indicates a retrieval operation for historical alarm data. The 'get' prefix and 'history' suffix are consistent with query/fetch operations that do not modify state.
Attacks that exploit this kind of access
get_alarm_history. 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_alarm_history: 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_alarm_history 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_alarm_history 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_alarm_history. 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_alarm_history 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.