AI agents call gandi_mailbox_get_mailbox to retrieve information from Gandi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves mailbox information by address without creating, modifying, deleting, or executing operations. It is a read-only query operation with minimal blast radius if misused by an AI agent—worst case being unauthorized access to mailbox metadata already associated with the account/organization being queried.
From the tool's definition Tool name contains 'get' and description states 'Get a single mailbox by address', indicating retrieval of existing data without modification or deletion.
Attacks that exploit this kind of access
Get a single mailbox by address (current mailbox product). It is categorised as a Read tool in the Gandi MCP Server, which means it retrieves data without modifying state.
Register the Gandi MCP server in PolicyLayer and add a rule for gandi_mailbox_get_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 Gandi. Nothing to install.
gandi_mailbox_get_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 gandi_mailbox_get_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 gandi_mailbox_get_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.
gandi_mailbox_get_mailbox is provided by the Gandi MCP server (millsymills-com/gandi-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 →