AI agents use alexa_add_list_item to create or update resources in Alexa — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Alexa environment.
This tool creates or modifies data (adds an item to a list) without permanent consequences. It is categorized as Write rather than Read (retrieves data), Execute (runs code/commands), Destructive (irreversibly deletes), or Financial (moves money). The severity is low because misuse would only result in unwanted list items that are trivially reversible and cause no harm to system integrity or user data security.
From the tool's definition Tool adds an item to an Alexa list (shopping, to-do, etc), which creates or modifies data reversibly. The operation is non-destructive and can be easily undone by removing the item.
Attacks that exploit this kind of access
Add an item to an Alexa list (shopping, to-do, etc). It is categorised as a Write tool in the Alexa MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Alexa MCP server in PolicyLayer and add a rule for alexa_add_list_item: 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_add_list_item is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the alexa_add_list_item 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_add_list_item. 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_add_list_item 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 →