Move reminder to permanent notes
AI agents use move_to_notes to create or update resources in MCP Reminders — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Reminders environment.
The action is reversible (notes can be edited or deleted later) and creates/modifies data rather than executing arbitrary code or destroying data. It's a Write operation. Severity is medium because misuse could clutter the notes system with unwanted persistent data, but the blast radius is limited to the user's own notes and the impact is reversible.
From the tool's definition Tool description states 'Move reminder to permanent notes' — this creates or modifies a permanent data store by converting a temporary reminder into a persistent note.
Attacks that exploit this kind of access
Move reminder to permanent notes. It is categorised as a Write tool in the MCP Reminders MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Reminders MCP server in PolicyLayer and add a rule for move_to_notes: 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 Reminders. Nothing to install.
move_to_notes 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 move_to_notes 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 move_to_notes. 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.
move_to_notes is provided by the MCP Reminders MCP server (mikeybeez/mcp-reminders). 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 →