查询我的最近订单。
AI agents call my_orders 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 retrieves historical order information for the authenticated user. It performs a passive query with no side effects, no data modification, and no external command execution. The blast radius of misuse is minimal—an agent could only retrieve order history that likely belongs to the user context. This is a classic Read category operation.
From the tool's definition Tool name is 'my_orders' and description translates to 'Query my recent orders' - a straightforward retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
查询我的最近订单。. 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 my_orders: 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.
my_orders 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 my_orders 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 my_orders. 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.
my_orders 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 →