AI agents call search_adlibrary_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 |
|---|---|---|---|
ids | array | — | Filter by product IDs |
page | integer | — | Page number |
currency | array | — | Currency filter, e.g. ["USD","EUR"] |
order_by | string | — | Sort field |
per_page | integer | — | Results per page, max 100 |
ad_status | number | — | Ad status: 1=Active, 2=Stopped |
direction | string | — | Sort direction: "asc" or "desc" |
ad_forecast | array | — | Ad forecast filter |
category_id | array | — | Filter by category IDs |
price_usd_end | number | — | Maximum price in USD |
active_days_end | number | — | Maximum active days |
ad_ended_at_end | number | — | Ad end time end (unix timestamp) |
Parameters from the server's own tool schema.
This tool retrieves and queries advertising data from Meta's Ad Library without modifying, deleting, or executing operations. It is purely informational/investigative in nature, searching through existing ad library records. No side effects or data modifications occur. The credit consumption model is typical for read-only API operations that consume resources per query result.
From the tool's definition Tool performs a search operation on Meta Ad Library products with filtering capabilities (price, platform, ad status, active days). The description uses 'Search' and filtering language with no mention of modification, deletion, or execution of code.
Risk signalsHigh parameter count (20 properties)
Attacks that exploit this kind of access
Search Meta Ad Library products. Filter by price, platform, ad status, active 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_adlibrary_products accepts 12 parameters: ids, page, currency, order_by, per_page, ad_status, direction, ad_forecast, category_id, price_usd_end, active_days_end, ad_ended_at_end. 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_adlibrary_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.
search_adlibrary_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 search_adlibrary_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 search_adlibrary_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.
search_adlibrary_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 →