Update an existing reminder
AI agents use update_reminder to create or update resources in MCP Calendar Assistant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Calendar Assistant environment.
This tool modifies reminder metadata (e.g., time, text, status) but does not delete the reminder or execute arbitrary code. The change is reversible—users can update again or undo through normal calendar operations.
From the tool's definition Tool name 'update_reminder' and description 'Update an existing reminder' indicate modification of existing data. The verb 'update' is explicitly a Write operation that changes reminder properties reversibly.
Attacks that exploit this kind of access
Update an existing reminder. It is categorised as a Write tool in the MCP Calendar Assistant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Calendar Assistant MCP server in PolicyLayer and add a rule for update_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 MCP Calendar Assistant. Nothing to install.
update_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 update_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 update_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.
update_reminder is provided by the MCP Calendar Assistant MCP server (momer17/mailmcp). 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 →