search_products_by_brand
AI agents call search_products_by_brand 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.
Despite an empty description, the naming pattern, sibling tools, and system context (product recommendation system using vector search) make it clear this tool retrieves/filters product data by brand. No capability to modify, delete, execute code, or commit financial actions. Confidence is high due to strong contextual evidence, though slightly reduced due to missing tool description.
From the tool's definition Tool name 'search_products_by_brand' combined with sibling tools that are all retrieval-oriented (get_brands, get_categories, search_products, search_products_by_category, etc.) and server description stating 'semantic search and natural language product…
Attacks that exploit this kind of access
search_products_by_brand. 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_by_brand: 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_by_brand 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_by_brand 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_by_brand. 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_by_brand 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 →