Find fashion products using natural language and/or structured filters. Provide a query for semantic ranking via multimodal text+image embeddings ("oversized wool coat", "black leather jacket", "minimalist gold jewelry", "linen shirt for a beach wedding under $200") — best for open-ended discover...
Risk signalsAccepts freeform code/query input (query) · High parameter count (24 properties)
Part of the Market server.
Free to start. No card required.
AI agents call discover_products to retrieve information from Market without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though discover_products only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"discover_products": {}
}
}See the full Market policy for all 6 tools.
These attack patterns abuse exactly the kind of access discover_products gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Find fashion products using natural language and/or structured filters. Provide a query for semantic ranking via multimodal text+image embeddings ("oversized wool coat", "black leather jacket", "minimalist gold jewelry", "linen shirt for a beach wedding under $200") — best for open-ended discovery. Keep queries concrete: noun-led with up to one or two modifiers works best ("summer linen shirt" beats "breathable linen shirt perfect for summer"). Provide only structured filters (category, brand, colors, gender, price, etc.) for pure browse — results are recency-ranked and paginate cleanly. Combine both for filtered semantic search. At least one of query or a filter must be provided. Example calls (notice the sparse filter population — descriptive attributes stay in query, not in structured fields): - "linen wedding guest dress under $200" → {query: "linen wedding guest dress", gender: "women", max_price: 200, materials: ["linen"]} - "wool coat under $300" → {query: "wool coat", gender: "women", max_price: 300, materials: ["wool"]} - "browse women's black dresses $100-$300" → {gender: "women", category: "clothing/dresses", colors: ["black"], min_price: 100, max_price: 300} - "Acne Studios outerwear" → {query: "outerwear", brand: "Acne Studios", gender: "women"} Returns compact product cards: AI-generated summary, price, images, tags, and compact availability by color/size; variant price differences are nested under the availability dimension that determines price. For merchant description, store info, SKU-level variants, exact variant prices, and all product images, call get_product with a product ID from these results. Multi-currency prices supported (e.g. "under 200 zł" or min_price=200 + currency="PLN"); returned prices render in the requested currency when provided.. It is categorised as a Read tool in the Market MCP Server, which means it retrieves data without modifying state.
Register the Market MCP server in PolicyLayer and add a rule for discover_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 Market. Nothing to install.
discover_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 discover_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 discover_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.
discover_products is provided by the Market MCP server (https://api.vistoya.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Market tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.