search_products_by_category
AI agents call search_products_by_category to retrieve information from Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query/filter products by category within an Elasticsearch-backed e-commerce system. This is a read operation with no side effects—it retrieves data without modifying, deleting, or executing arbitrary code. The empty description slightly reduces confidence, but the naming convention and peer tools (search, search_products_by_brand) strongly indicate a safe read-only query.
From the tool's definition Tool name 'search_products_by_category' and server context indicating search/query functionality for e-commerce data. Sibling tools include 'search' and 'search_products_by_brand', which are clearly retrieval operations.
Attacks that exploit this kind of access
search_products_by_category. It is categorised as a Read tool in the Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Search MCP server in PolicyLayer and add a rule for search_products_by_category: 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 Search MCP. Nothing to install.
search_products_by_category 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_category 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_category. 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_category is provided by the Search MCP server (piscaries/search_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 →