Find a specific mailbox by name or role
AI agents call find_mailbox to retrieve information from FastMail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a lookup operation to identify a mailbox based on matching criteria. It is a Read operation as defined by the schema: retrieves or queries data with no side effects. The severity is low because accessing mailbox metadata does not expose sensitive email content (that would be get_email_body) and cannot be misused to cause harm without additional tools.
From the tool's definition Tool description states 'Find a specific mailbox by name or role' - a query operation that retrieves metadata about mailboxes without modifying data. The verb 'find' indicates a retrieval/search operation. No side effects or state changes are implied.
Attacks that exploit this kind of access
Find a specific mailbox by name or role. It is categorised as a Read tool in the FastMail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FastMail MCP Server MCP server in PolicyLayer and add a rule for find_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 FastMail MCP Server. Nothing to install.
find_mailbox 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 find_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 find_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.
find_mailbox is provided by the FastMail MCP Server MCP server (jmhron/fastmailmcp). 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 →