AI agents use mark_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.
Marking messages (flagging/unflagging) modifies email state reversibly—users can undo flag changes. This is Write rather than Read (which only retrieves data) or Destructive (flags are not deleted, just toggled).
From the tool's definition Tool modifies message flags via IMAP (add/remove standard flags), which is a reversible state change on email messages. The description explicitly states 'Add or remove' flags, indicating write operations that alter message metadata.
Attacks that exploit this kind of access
Add or remove standard IMAP flags on messages. 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 mark_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.
mark_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 mark_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 mark_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.
mark_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 →