Get tasks without due dates using icalPal.
AI agents call get_undated_tasks to retrieve information from icalPal 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 task data from macOS Reminders without creating, modifying, deleting, or executing any operations. It has no side effects beyond reading existing data. The blast radius of misuse is minimal—an AI could only retrieve task information the user already has access to. Low severity because access is scoped to the user's own calendar/reminder data.
From the tool's definition Tool name 'get_undated_tasks' and description 'Get tasks without due dates' indicate a query operation that retrieves data without modification.
Attacks that exploit this kind of access
Get tasks without due dates using icalPal. It is categorised as a Read tool in the icalPal MCP Server MCP Server, which means it retrieves data without modifying state.
Register the icalPal MCP Server MCP server in PolicyLayer and add a rule for get_undated_tasks: 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 icalPal MCP Server. Nothing to install.
get_undated_tasks 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_undated_tasks 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_undated_tasks. 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_undated_tasks is provided by the icalPal MCP Server MCP server (wsargent/icalpal-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 →