Move emails to a different mailbox
AI agents use mail_move to create or update resources in MCP Apple Mail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Apple Mail environment.
Moving emails between mailboxes modifies email metadata and organization state reversibly. It is not destructive (deletion is handled by mail_delete), not execute (no arbitrary code execution), not financial. It qualifies as Write because it alters data state.
From the tool's definition Tool name 'mail_move' and description 'Move emails to a different mailbox' indicate modifying email location/state. This is a reversible operation (emails can be moved back), distinct from deletion.
Attacks that exploit this kind of access
Move emails to a different mailbox. It is categorised as a Write tool in the MCP Apple Mail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Apple Mail MCP server in PolicyLayer and add a rule for mail_move: 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 Apple Mail. Nothing to install.
mail_move 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 mail_move 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 mail_move. 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.
mail_move is provided by the MCP Apple Mail MCP server (lionsr/mcp-apple). 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 →