AI agents use archive_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.
Archiving messages modifies email organization by moving them to a designated folder. This is a Write operation because it reversibly changes data state without destroying it—the messages remain accessible in the Archive folder and can be moved elsewhere or restored. Severity is medium because misuse could obscure important messages from the inbox (affecting visibility/workflow) but causes no data loss.
From the tool's definition Tool 'archive_messages' moves messages to the Archive folder, which is a reversible modification of message state/location.
Attacks that exploit this kind of access
Archive messages — moves them to the Archive folder. 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 archive_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.
archive_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 archive_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 archive_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.
archive_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 →