List all available Siri shortcuts
AI agents call list_shortcuts to retrieve information from Siri Shortcuts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation—listing/querying available shortcuts. It has no side effects, does not execute code, modify data, or trigger external operations. The blast radius is minimal since it only exposes metadata about available shortcuts. Severity is low as an AI agent listing shortcuts poses minimal risk.
From the tool's definition Tool name 'list_shortcuts' and description 'List all available Siri shortcuts' indicate a query operation that retrieves and enumerates shortcuts without modification or execution.
Attacks that exploit this kind of access
List all available Siri shortcuts. It is categorised as a Read tool in the Siri Shortcuts MCP Server, which means it retrieves data without modifying state.
Register the Siri Shortcuts MCP server in PolicyLayer and add a rule for list_shortcuts: 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 Siri Shortcuts. Nothing to install.
list_shortcuts 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 list_shortcuts 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 list_shortcuts. 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.
list_shortcuts is provided by the Siri Shortcuts MCP server (mcp-server-siri-shortcuts). 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 →