Search for products on Coupang by keyword.
AI agents call search_products to retrieve information from Coupang 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 product information from an e-commerce API based on search parameters. It has no side effects—it only reads and returns data to the user. The blast radius of misuse is minimal; even if an agent performs excessive searches, it causes no harm to data or operations. This is a straightforward Read operation.
From the tool's definition Tool name 'search_products' and description 'Search for products on Coupang by keyword' indicate a query/retrieval operation. No modifications, deletions, code execution, or financial transactions are performed.
Attacks that exploit this kind of access
Search for products on Coupang by keyword. It is categorised as a Read tool in the Coupang MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Coupang MCP Server MCP server in PolicyLayer and add a rule for search_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 Coupang MCP Server. Nothing to install.
search_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 search_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 search_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.
search_products is provided by the Coupang MCP Server MCP server (space-cap/mcp-coupang-server). 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 →