gandi_mailbox_update_mailbox · Gandi MCP: Risk & Policy

WHAT IT DOES

What gandi_mailbox_update_mailbox does on Gandi

AI agents use gandi_mailbox_update_mailbox to create or update resources in Gandi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gandi environment.

WHY IT NEEDS A POLICY

Why gandi_mailbox_update_mailbox needs a policy

This tool creates or modifies mailbox data reversibly, fitting the Write category. Severity is medium because mailbox updates could disrupt email service or expose user data if misconfigured by an agent, but changes are typically reversible through subsequent updates. The Gandi billing/production context elevates severity from low to medium due to potential customer impact.

From the tool's definition Tool name contains 'update_mailbox' which performs modification of mailbox configuration/settings. Description explicitly states 'Update a mailbox' indicating reversible changes to mailbox properties (not deletion).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gandi_mailbox_update_mailbox Rate-limited

gandi_mailbox_update_mailbox stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "gandi_mailbox_update_mailbox": {
      "limits": [
        {
          "counter": "gandi_mailbox_update_mailbox_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Gandi, so you can run agents against it safely.

FAQ

Questions about gandi_mailbox_update_mailbox

What does the gandi_mailbox_update_mailbox tool do? +

Update a mailbox (current mailbox product, not legacy email). It is categorised as a Write tool in the Gandi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on gandi_mailbox_update_mailbox? +

Register the Gandi MCP server in PolicyLayer and add a rule for gandi_mailbox_update_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.

What risk level is gandi_mailbox_update_mailbox? +

gandi_mailbox_update_mailbox is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit gandi_mailbox_update_mailbox? +

Yes. Add a rate_limit block to the gandi_mailbox_update_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.

How do I block gandi_mailbox_update_mailbox completely? +

Set action: deny in the PolicyLayer policy for gandi_mailbox_update_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.

What MCP server provides gandi_mailbox_update_mailbox? +

gandi_mailbox_update_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.