AI agents use create_reminder to create or update resources in Todoist — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todoist environment.
This tool creates a new reminder, which is a reversible write operation. It adds metadata to a task but does not modify the task itself, execute arbitrary code, delete data, or move money. The impact is limited to adding a notification schedule, making it a straightforward Write categorization with low severity since reminders are easily removed.
From the tool's definition Tool name is 'create_reminder' and description states 'Create a reminder for a task.' The verb 'Create' indicates data creation/modification.
Attacks that exploit this kind of access
Create a reminder for a task. Requires Todoist Pro. It is categorised as a Write tool in the Todoist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todoist MCP server in PolicyLayer and add a rule for create_reminder: 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 Todoist. Nothing to install.
create_reminder 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 create_reminder 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 create_reminder. 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.
create_reminder is provided by the Todoist MCP server (sjvadrevu/todoist-mcp-server). 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 →