AI agents use set_reminder_preferences to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool modifies reminder preferences, which is a reversible configuration change with no side effects beyond storing user settings. It does not delete data (not Destructive), execute external code (not Execute), create new tasks or records (Write rather than more severe), or involve financial transactions (not Financial).
From the tool's definition Tool name 'set_reminder_preferences' and description 'Update local reminder preferences' indicate modification of configuration data. The word 'Update' explicitly signals a write operation that changes stored preferences.
Attacks that exploit this kind of access
Update local reminder preferences. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for set_reminder_preferences: 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 Todos. Nothing to install.
set_reminder_preferences 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 set_reminder_preferences 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 set_reminder_preferences. 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.
set_reminder_preferences is provided by the Todos MCP server (@hasna/todos). 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 →