AI agents call search_ads 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 | number | — | Sort by: 1=Last found time, 2=Create time(default), 3=First found time, 4=Ad plays, 5=Delivery days, 6=Engagement, 7=Like rate, 9=Like count, 21=Ad spend |
is_app | boolean | — | Filter: has APP product |
is_url | number | — | URL status: 0=No landing page, 1=Has landing page |
region | array | — | Country/region codes, e.g. ["US","GB","DE"] |
data_type | array | — | Data type filter: 1=Hot Product, 2=Mini Shop Ad, 3=E-commerce, 4=Spark Ads, 5=Game, 6=App, 7=AI, 8=Short Drama |
page_size | integer | — | Results per page, max 50 |
plat_type | number | — | Platform: 1=TikTok, 2=Facebook. Omit for all platforms |
shop_type | array | — | E-commerce platform filter, e.g. ["shopify","woocommerce","magento","wix","shoplazza","shopline","squarespace","shopyy"] |
sort_type | string | — | Sort order: "desc"(default) or "asc" |
is_product | boolean | — | Filter: has ad product |
ad_cost_max | number | — | Maximum ad spend (USD) |
ad_cost_min | number | — | Minimum ad spend (USD) |
Parameters from the server's own tool schema.
This tool retrieves and queries advertising data across social platforms. While it consumes credits (a consumption tracking mechanism), it does not move money, execute code, modify data, or cause irreversible changes. It is a passive search and filter operation, making it a Read category tool.
From the tool's definition Tool description states it 'Search[es] ad videos' with filtering capabilities. The verb 'search' and the phrase '1 credit per result' indicate data retrieval with no modification or deletion.
Risk signalsHigh parameter count (35 properties)
Attacks that exploit this kind of access
Search ad videos across TikTok and Facebook. Filter by keyword, region, platform, engagement, ad spend, delivery days. 1 credit per result. It is categorised as a Read tool in the Pipiads MCP Server, which means it retrieves data without modifying state.
search_ads accepts 12 parameters: sort, is_app, is_url, region, data_type, page_size, plat_type, shop_type, sort_type, is_product, ad_cost_max, ad_cost_min. 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 search_ads: 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.
search_ads 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_ads 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_ads. 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_ads 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 →