AI agents call alexa_list_devices to retrieve information from Alexa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and displays information about existing devices. It performs no write, deletion, execution, or financial operations. The read of device inventory poses minimal risk; an AI agent cannot cause harm by listing devices. Severity is low because the information exposed (device types and status) is generally non-sensitive in the context of an account holder's own devices.
From the tool's definition Tool description states 'List all Amazon Echo devices in your account' — a query operation that retrieves device metadata (serial numbers, types, online status) with no modification or side effects.
Attacks that exploit this kind of access
List all Amazon Echo devices in your account with their serial numbers, types, and online status. It is categorised as a Read tool in the Alexa MCP Server, which means it retrieves data without modifying state.
Register the Alexa MCP server in PolicyLayer and add a rule for alexa_list_devices: 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 Alexa. Nothing to install.
alexa_list_devices 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 alexa_list_devices 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 alexa_list_devices. 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.
alexa_list_devices is provided by the Alexa MCP server (serversmx/alexa-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →