AI agents use meta.ads.create to create or update resources in Ads — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ads environment.
This tool creates a new Meta ad object, which is a reversible write operation (the ad can be deleted or modified later). It defaults to PAUSED status and dry-run mode, limiting immediate blast radius. While it involves advertising infrastructure that could lead to spend, it does not directly move money or commit financial obligations — it merely creates a paused ad unit.
From the tool's definition 'Create a Meta ad under an existing ad set, attaching a previously-created creative. Defaults to status=PAUSED. Dry-run by default.'
Attacks that exploit this kind of access
Create a Meta ad under an existing ad set, attaching a previously-created creative. Defaults to status=PAUSED. Dry-run by default. It is categorised as a Write tool in the Ads MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ads MCP server in PolicyLayer and add a rule for meta.ads.create: 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 Ads. Nothing to install.
meta.ads.create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the meta.ads.create 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 meta.ads.create. 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.
meta.ads.create is provided by the Ads MCP server (manlikemuneeb/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 →