search_products
AI agents call search_products to retrieve information from Product Recommendation System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries product data from a vector store without side effects. The empty description and naming pattern with other read-only siblings (all search/get operations) confirm it is a data retrieval operation. No capability to create, modify, delete, or execute arbitrary code is evident. Severity is low because misuse would only return product information, causing no harm.
From the tool's definition Tool name 'search_products' combined with sibling tools all using 'search' and 'get' prefixes (search_products_by_brand, search_products_by_category, get_brands, get_product_description) indicates query/retrieval functionality.
Attacks that exploit this kind of access
search_products. It is categorised as a Read tool in the Product Recommendation System MCP Server, which means it retrieves data without modifying state.
Register the Product Recommendation System 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 Product Recommendation System. 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 Product Recommendation System MCP server (josephazar/products-recommendation-mcp-maf). 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 →