find_products
Answer 'best <category> under $N' and 'which <category> has the most <spec>' directly: filter a category by maxPriceUsd and/or brand, then rank by a field — 'priceUsd' (default, cheapest first), 'releaseDate', or any of the category's spec keys (set descending:true for biggest-first, e.g. sortBy:...
This record as markdown: /tools/com-frontdeskreview-front-desk-review-data/find-products.md
What find_products does on The Front Desk Review
AI agents call find_products to retrieve information from The Front Desk Review without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
brand | string | — | Only products from this brand. |
sortBy | string | — | Field to rank by: 'priceUsd' (default), 'releaseDate', or a spec key from the category. |
category | string | Yes | Product category slug from list_product_categories. |
descending | boolean | — | Rank largest/newest first (default false = smallest/cheapest first). |
maxPriceUsd | number | — | Only products at or below this USD price. |
Parameters from the server's own tool schema.
Why find_products is rated Low
find_products is a search and ranking tool that retrieves and queries product data without modifying, deleting, or executing any operations. It performs filtering and sorting on existing product records, which are classic Read category operations. The low severity reflects that misuse would at worst return incorrect product recommendations with no side effects.
From the tool's definition Tool description states it 'filter[s] a category' and 'rank[s]' products, 'Returns provenanced product records'. The verbs are retrieval-focused: filter, rank, return. No mutations, deletions, executions, or financial operations are mentioned.
Attacks that exploit this kind of access
The rule that runs find_products safely
PolicyLayer is an MCP gateway: it sits between your AI agents and The Front Desk Review, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For find_products, this is the rule to start with:
find_products is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect The Front Desk Review, apply this rule, and every find_products call is checked against it from then on.
Questions about find_products
Answer 'best <category> under $N' and 'which <category> has the most <spec>' directly: filter a category by maxPriceUsd and/or brand, then rank by a field — 'priceUsd' (default, cheapest first), 'releaseDate', or any of the category's spec keys (set descending:true for biggest-first, e.g. sortBy:'battery_mah' descending:true). Returns provenanced product records; products missing the sort value sort last. Never infers a spec it has not verified. It is categorised as a Read tool in the The Front Desk Review MCP Server, which means it retrieves data without modifying state.
find_products accepts 5 parameters: brand, sortBy, category, descending, maxPriceUsd. Required: category. The full parameter table on this page comes from the server's own tool schema.
Register the The Front Desk Review MCP server in PolicyLayer and add a rule for find_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 The Front Desk Review. Nothing to install.
find_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 find_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 find_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.
find_products is provided by the The Front Desk Review MCP server (https://mcp.frontdeskreview.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on The Front Desk Review, and thousands of servers like it.
This server
Across the catalogue