AI agents call alexa_query_device 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 retrieves device status information without modifying, deleting, or executing actions. It performs a read-only query operation on smart home device state, producing no side effects. The low severity reflects minimal blast radius—misuse would only expose device status data, not cause unintended device actions or data destruction.
From the tool's definition Tool name 'alexa_query_device' and description 'Query the current state of one or more smart home devices (on/off, brightness, temperature, etc)' explicitly indicate state retrieval with no modifications.
Attacks that exploit this kind of access
Query the current state of one or more smart home devices (on/off, brightness, temperature, etc). 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_query_device: 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_query_device 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_query_device 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_query_device. 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_query_device 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 →