查看或设置偏好：常用门店、默认口味（冰/热、糖度、杯型），并可查看最近订单与常点商品。
AI agents call preferences to retrieve information from Luckin Mcp Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool primarily retrieves user preferences, order history, and product data without triggering external operations or modifying critical data. The write component is limited to reversible preference updates. No payment processing, order creation/deletion, or system-level command execution is involved. Classification as Read with low severity is appropriate.
From the tool's definition Tool description explicitly states '查看或设置偏好' (view or set preferences), '查看最近订单' (view recent orders), and '常点商品' (frequently ordered items). The primary functions are retrieval-focused: viewing preferences, recent orders, and product history.
Attacks that exploit this kind of access
查看或设置偏好：常用门店、默认口味（冰/热、糖度、杯型），并可查看最近订单与常点商品。. It is categorised as a Read tool in the Luckin Mcp Proxy MCP Server, which means it retrieves data without modifying state.
Register the Luckin Mcp Proxy MCP server in PolicyLayer and add a rule for preferences: 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 Luckin Mcp Proxy. Nothing to install.
preferences 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 preferences 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 preferences. 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.
preferences is provided by the Luckin Mcp Proxy MCP server (wyhacc/luckin-mcp-proxy). 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 →