mail_create_mailbox
AI agents use mail_create_mailbox 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.
The tool creates a new mailbox, which is a reversible write operation that modifies the email account structure. It is not a read-only operation (no query/fetch semantics), not immediately destructive (mailbox can be deleted), and not financial.
From the tool's definition Tool name 'mail_create_mailbox' indicates creation of a new mailbox/folder. Combined with server description stating it provides 'full access to Fastmail accounts for managing email', this is a write operation that creates a new email organizational structure.
Attacks that exploit this kind of access
mail_create_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_create_mailbox: 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_create_mailbox 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_create_mailbox 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_create_mailbox. 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_create_mailbox 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 →