get_alarm_history
AI agents call get_alarm_history to retrieve information from AWS IoT SiteWise 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 or queries historical alarm data without side effects. It follows the Read category pattern (get, fetch, query) and has low blast radius even if misused—worst case would be exposure of already-recorded alarm history. The empty description lowers confidence slightly, but the naming convention strongly suggests a read operation.
From the tool's definition Tool name 'get_alarm_history' indicates retrieval of historical alarm data. The 'get_' prefix is a standard read operation pattern. No indication of modification, deletion, or execution.
Attacks that exploit this kind of access
get_alarm_history. It is categorised as a Read tool in the AWS IoT SiteWise MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS IoT SiteWise 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 AWS IoT SiteWise 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 AWS IoT SiteWise MCP Server MCP server (awslabs.aws-iot-sitewise-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.