AI agents call gandi_email_list_mailboxes 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.
The tool retrieves or queries email mailbox data without side effects. Despite the empty description reducing confidence slightly, the name clearly denotes a list/read operation typical of query tools. No capability to modify, delete, or execute is suggested. Classified as Read with low severity due to limited blast radius if misused—disclosure of mailbox metadata rather than destructive or financial harm.
From the tool's definition Tool name 'gandi_email_list_mailboxes' indicates retrieval of mailbox information; no modification, deletion, or execution implied.
Attacks that exploit this kind of access
gandi_email_list_mailboxes. 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_email_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 Gandi. Nothing to install.
gandi_email_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 gandi_email_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 gandi_email_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.
gandi_email_list_mailboxes 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 →