AI agents use move_messages to create or update resources in Mail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mail environment.
The move_messages tool performs a state modification (relocating messages between folders) that is reversible and does not destroy data. This fits the Write category. Severity is medium because misuse could result in emails being hidden or organized incorrectly, causing workflow disruption or potential loss of visibility into important messages, but the action itself is not permanent and can be undone by moving…
From the tool's definition Tool description states 'Move messages from one folder to another' — this modifies the state of email messages by changing their location/folder assignment. It is a reversible operation (messages can be moved back), distinguishing it from destructive deletion.
Attacks that exploit this kind of access
Move messages from one folder to another. It is categorised as a Write tool in the Mail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mail MCP server in PolicyLayer and add a rule for move_messages: 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 Mail. Nothing to install.
move_messages 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_messages 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_messages. 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_messages is provided by the Mail MCP server (kpihx/mail-mcp). 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 →