gandi_mailbox_create_forward · Gandi MCP: Risk & Policy

WHAT IT DOES

What gandi_mailbox_create_forward does on Gandi

AI agents use gandi_mailbox_create_forward 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_create_forward needs a policy

This tool creates new email forwarding rules, which is a reversible write operation. It modifies email configuration by adding a forward destination, but the action can be undone (by deleting or modifying the forward). It does not execute arbitrary code, delete data, or move money, so Write is the appropriate category.

From the tool's definition Create a mailbox forward (current mailbox product). The verb 'create' indicates a write operation that adds a new forwarding rule to the mailbox system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gandi_mailbox_create_forward Rate-limited

gandi_mailbox_create_forward 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_create_forward": {
      "limits": [
        {
          "counter": "gandi_mailbox_create_forward_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_create_forward

What does the gandi_mailbox_create_forward tool do? +

Create a mailbox forward (current mailbox product). 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_create_forward? +

Register the Gandi MCP server in PolicyLayer and add a rule for gandi_mailbox_create_forward: 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_create_forward? +

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

Can I rate-limit gandi_mailbox_create_forward? +

Yes. Add a rate_limit block to the gandi_mailbox_create_forward 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_create_forward completely? +

Set action: deny in the PolicyLayer policy for gandi_mailbox_create_forward. 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_create_forward? +

gandi_mailbox_create_forward 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.