Return metadata for the current ad account (id, name, urls, timezone, currency).
AI agents call get_ad_account to retrieve information from OpenAI Ads MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries ad account information without creating, modifying, deleting, or executing any operations. It is purely informational and poses minimal risk in terms of misuse by an AI agent, though the account metadata itself could be sensitive information in some contexts.
From the tool's definition Tool returns account metadata (id, name, urls, timezone, currency) with no modification or side effects. Description explicitly states 'Return' indicating data retrieval only.
Attacks that exploit this kind of access
Return metadata for the current ad account (id, name, urls, timezone, currency). It is categorised as a Read tool in the OpenAI Ads MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenAI Ads MCP Server MCP server in PolicyLayer and add a rule for get_ad_account: 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 OpenAI Ads MCP Server. Nothing to install.
get_ad_account 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 get_ad_account 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 get_ad_account. 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.
get_ad_account is provided by the OpenAI Ads MCP Server MCP server (roast-labs/openai-ads-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 →