AI agents use move_message to create or update resources in Inbox — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Inbox environment.
The move_message tool modifies email state by relocating messages between folders and potentially creating new folders. This is a Write operation because it creates or modifies data reversibly—messages can be moved back, and folders can be deleted. It is not Destructive because messages are not deleted or permanently lost.
From the tool's definition Tool description states 'Move one or more messages to a different folder. Creates the target folder if needed.' This is a reversible modification operation that changes message location and can create folders.
Attacks that exploit this kind of access
Move one or more messages to a different folder. Creates the target folder if needed. It is categorised as a Write tool in the Inbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Inbox MCP server in PolicyLayer and add a rule for move_message: 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 Inbox. Nothing to install.
move_message 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_message 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_message. 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_message is provided by the Inbox MCP server (p-w-4-z/inbox-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 →