Order a new Brighty card. Two-step: first POST /cards/order/intent (returns fees, amount, and a short-lived hash), then POST /cards/order with hash + fees + sourceAccountId and a fresh UUIDv4 Idempotency-Key. Always show the user intent.fees + intent.amount before executing the order. Returns { i...
AI agents use brighty_order_card to commit financial operations through Brighty MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Ordering a card commits financial obligations (fees and amount debited from sourceAccountId) and initiates a banking product issuance. This falls squarely in the Financial category as it charges the user's account and creates a new payment instrument.
From the tool's definition Order a new Brighty card... POST /cards/order with hash + fees + sourceAccountId... Always show the user intent.fees + intent.amount before executing the order
Attacks that exploit this kind of access
Order a new Brighty card. Two-step: first POST /cards/order/intent (returns fees, amount, and a short-lived hash), then POST /cards/order with hash + fees + sourceAccountId and a fresh UUIDv4 Idempotency-Key. Always show the user intent.fees + intent.amount before executing the order. Returns { intent, card, idempotencyKey }. It is categorised as a Financial tool in the Brighty MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Brighty MCP Server MCP server in PolicyLayer and add a rule for brighty_order_card: 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 Brighty MCP Server. Nothing to install.
brighty_order_card 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 brighty_order_card 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 brighty_order_card. 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.
brighty_order_card is provided by the Brighty MCP Server MCP server (razz-team/brighty-agent-toolkit). 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 →