查询支付状态（收银台下单后的支付结果）。
AI agents call cashier_pay_query to retrieve information from Coffee Company MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries payment status information—a read-only operation that retrieves existing data about payment results. While it accesses financial transaction data (which could inform fraud or privacy concerns), it does not move money, modify records, or execute financial operations.
From the tool's definition Tool name 'cashier_pay_query' and description '查询支付状态（收银台下单后的支付结果）' [Query payment status (payment result after cashier order)] indicate retrieval of payment information without modification.
Attacks that exploit this kind of access
查询支付状态（收银台下单后的支付结果）。. It is categorised as a Read tool in the Coffee Company MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Coffee Company MCP Server MCP server in PolicyLayer and add a rule for cashier_pay_query: 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 Coffee Company MCP Server. Nothing to install.
cashier_pay_query 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 cashier_pay_query 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 cashier_pay_query. 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.
cashier_pay_query is provided by the Coffee Company MCP Server MCP server (sawzhang/coffee-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 →