mail_list_mailboxes
AI agents call mail_list_mailboxes to retrieve information from Pyfastmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a list of mailboxes from a Fastmail account. Listing operations have no side effects—they retrieve data without creating, modifying, deleting, or executing anything. The lack of a description lowers confidence slightly, but the tool name is sufficiently clear and aligns with standard read operations in email protocols (JMAP).
From the tool's definition Tool name 'mail_list_mailboxes' indicates a listing operation that retrieves mailbox information without modification. The 'list' verb and mailbox context strongly suggest read-only data retrieval.
Attacks that exploit this kind of access
mail_list_mailboxes. It is categorised as a Read tool in the Pyfastmail MCP Server, which means it retrieves data without modifying state.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for mail_list_mailboxes: 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_list_mailboxes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mail_list_mailboxes 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_list_mailboxes. 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_list_mailboxes 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 →