AI agents call get_discount to retrieve information from Creem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing discount information without modifying, deleting, or creating any data. It is a simple read operation on discount metadata. No financial obligations are committed, no data is destructively removed, and no code execution is triggered. The blast radius of misuse is minimal—an attacker could enumerate discount codes but cannot create fraudulent discounts or process unauthorized payments.
From the tool's definition Tool name 'get_discount' and description 'Retrieve discount code details' indicate a query operation with no side effects.
Attacks that exploit this kind of access
Retrieve discount code details. It is categorised as a Read tool in the Creem MCP Server, which means it retrieves data without modifying state.
Register the Creem MCP server in PolicyLayer and add a rule for get_discount: 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 Creem. Nothing to install.
get_discount is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_discount 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 get_discount. 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.
get_discount is provided by the Creem MCP server (selenium39/mcp-server-creem). 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 →