AI agents use gandi_email_refund_slot to commit financial operations through Gandi — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool processes refunds, which constitutes a financial obligation and reversal of charges. While it operates within a defined refund window (suggesting some guardrails exist), it still commits a financial transaction that moves credits or money. Financial operations are the most severe category per the hierarchy, superseding even destructive or execute operations due to their direct monetary impact.
From the tool's definition Tool name contains 'refund' and description explicitly states 'Refund/delete an unused slot (within the refund window)' — this moves money or credits back to a customer account, a financial transaction.
Attacks that exploit this kind of access
Refund/delete an unused slot (within the refund window). It is categorised as a Financial tool in the Gandi MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Gandi MCP server in PolicyLayer and add a rule for gandi_email_refund_slot: 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_refund_slot is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the gandi_email_refund_slot 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_refund_slot. 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_refund_slot 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 →