Apply a Starbucks Reward to your current cart. The reward will be used when you place the order.
AI agents use redeem_reward to commit financial operations through Mcp Starbucks — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Redeeming a reward is a financial action: it consumes a stored-value loyalty asset (Starbucks Reward) that has real monetary value. Once applied and the order is placed, the reward is irrevocably consumed, making this Financial in category. Misuse could drain a user's rewards balance without their intent.
From the tool's definition 'Apply a Starbucks Reward to your current cart. The reward will be used when you place the order.' — redeeming a reward commits a financial asset (loyalty points/reward) that is consumed upon order placement.
Attacks that exploit this kind of access
Apply a Starbucks Reward to your current cart. The reward will be used when you place the order. It is categorised as a Financial tool in the Mcp Starbucks MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Starbucks MCP server in PolicyLayer and add a rule for redeem_reward: 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 Mcp Starbucks. Nothing to install.
redeem_reward 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 redeem_reward 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 redeem_reward. 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.
redeem_reward is provided by the Mcp Starbucks MCP server (markswendsen-code/mcp-starbucks). 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 →