Create a single-image ad creative referencing a previously-uploaded image_hash. Builds a link_data object_story_spec under the hood. Dry-run by default. For video creatives, use passthrough.write until Phase 2.5 adds creatives.create_video.
AI agents use meta.creatives.create_image 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 ad creative resource in Meta Ads, which is a reversible write operation (the creative can be deleted later). It does not execute code, delete data, or move money. The dry-run default slightly lowers the immediate blast radius, but misuse could result in unintended live ad creatives being published, making severity medium.
From the tool's definition 'Create a single-image ad creative' and 'Dry-run by default' — the tool creates a new ad creative object in Meta Ads referencing an uploaded image hash
Attacks that exploit this kind of access
Create a single-image ad creative referencing a previously-uploaded image_hash. Builds a link_data object_story_spec under the hood. Dry-run by default. For video creatives, use passthrough.write until Phase 2.5 adds creatives.create_video. 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.creatives.create_image: 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.creatives.create_image 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.creatives.create_image 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.creatives.create_image. 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.creatives.create_image 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 →