從資料庫獲取產品資訊，可以根據產品名稱、類別、價格範圍進行查詢
AI agents call get_products to retrieve information from MCP E-commerce Demo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries product data from a database based on filter criteria. It has no side effects, does not modify data, and poses minimal risk if misused by an agent—worst case would be excessive queries or information disclosure of already-public product catalogs. Classification as Read is appropriate.
From the tool's definition Tool name 'get_products' and description '從資料庫獲取產品資訊，可以根據產品名稱、類別、價格範圍進行查詢' (retrieve product information from database, query by product name, category, price range) indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
從資料庫獲取產品資訊，可以根據產品名稱、類別、價格範圍進行查詢. It is categorised as a Read tool in the MCP E-commerce Demo MCP Server, which means it retrieves data without modifying state.
Register the MCP E-commerce Demo MCP server in PolicyLayer and add a rule for get_products: 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 E-commerce Demo. Nothing to install.
get_products 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_products 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_products. 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_products is provided by the MCP E-commerce Demo MCP server (uberr2000/mcp_demo). 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 →