AI agents call ai_search_image_products to retrieve information from Pipiads without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
sort | string | — | Sort field |
region | string | — | Country/region, comma-separated |
image_id | string | Yes | Image ID from submit response |
page_size | number | — | Results per page |
plat_type | number | — | Platform: 0=All, 1=TikTok, 2=Facebook |
price_max | number | — | Maximum price (USD) |
price_min | number | — | Minimum price (USD) |
sort_type | string | — | "asc" or "desc" |
current_page | number | — | Page number |
play_count_max | number | — | Maximum play count |
play_count_min | number | — | Minimum play count |
Parameters from the server's own tool schema.
This tool retrieves or queries product data based on image similarity matching. It does not create, modify, delete, execute code, or trigger financial transactions. The operation is read-only and returns results without altering any state. Severity is low as misuse would only expose existing product information, not enable unauthorized actions or data manipulation.
From the tool's definition Tool name and description indicate a search operation: 'Search products similar to a submitted image.' The verb 'search' and the query-like nature of retrieving product matches are characteristic of read operations with no side effects.
Risk signalsHigh parameter count (11 properties)
Attacks that exploit this kind of access
Search products similar to a submitted image. It is categorised as a Read tool in the Pipiads MCP Server, which means it retrieves data without modifying state.
ai_search_image_products accepts 11 parameters: sort, region, image_id, page_size, plat_type, price_max, price_min, sort_type, current_page, play_count_max, play_count_min. Required: image_id. The full parameter table on this page comes from the server's own tool schema.
Register the Pipiads MCP server in PolicyLayer and add a rule for ai_search_image_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 Pipiads. Nothing to install.
ai_search_image_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 ai_search_image_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 ai_search_image_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.
ai_search_image_products is provided by the Pipiads MCP server (pipiads-mcp-server). 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 →