search_ads
AI agents call search_ads to retrieve information from Meta Ad Library MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a public Ad Library without side effects. It performs a search query and returns read-only information (advertiser details, ad copy, reach metrics). No data is created, modified, deleted, or financial transactions occur. The severity is low because the Ad Library is publicly accessible and the tool only extracts existing information.
From the tool's definition Server description states the tool 'Searches the Meta (Facebook) Ad Library by keyword and returns ad details including advertiser, ad copy, and EU reach' — a query operation with no modification or deletion capability.
Attacks that exploit this kind of access
search_ads. It is categorised as a Read tool in the Meta Ad Library MCP MCP Server, which means it retrieves data without modifying state.
Register the Meta Ad Library 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 Meta Ad Library MCP. 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 Meta Ad Library MCP server (konstantin-tradient/meta-ad-library-mcp). 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 →