AI agents call list_mailboxes to retrieve information from Bichon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates mailbox folder structures (INBOX, Sent, etc.) but does not create, modify, delete, or execute any operations. It is a pure read operation with minimal blast radius—listing folders does not expose email contents and has no irreversible consequences. The low severity reflects that folder enumeration alone poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'list_mailboxes' and description 'List mailbox folders for an account' indicate a query operation that retrieves folder metadata without modification. The server description emphasizes 'search and read locally-archived emails' with no side effects.
Attacks that exploit this kind of access
List mailbox folders for an account (INBOX, Sent, etc.). It is categorised as a Read tool in the Bichon MCP Server, which means it retrieves data without modifying state.
Register the Bichon MCP server in PolicyLayer and add a rule for 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 Bichon. Nothing to install.
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 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 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.
list_mailboxes is provided by the Bichon MCP server (pras-labs/bichon-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 →