Move one or more emails to the Archive mailbox.
AI agents use mail_archive_email to create or update resources in Pyfastmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pyfastmail environment.
This tool changes email location/state (Write category) rather than permanently destroying data. While reversible, mass archival could hide important emails from inbox view, and an agent misusing this could archive critical messages, causing operational disruption. Severity is medium because the action is recoverable and doesn't meet the destructive or financial threshold.
From the tool's definition Tool moves emails to Archive mailbox. The action is reversible (emails can be moved back from Archive), modifying email organization state without deletion.
Attacks that exploit this kind of access
Move one or more emails to the Archive mailbox. It is categorised as a Write tool in the Pyfastmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for mail_archive_email: 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 Pyfastmail. Nothing to install.
mail_archive_email 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_archive_email 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_archive_email. 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_archive_email is provided by the Pyfastmail MCP server (pjosols/pyfastmail-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 →