Create a new ad set within a campaign
AI agents use create_ad_set to create or update resources in Meta Marketing API MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meta Marketing API MCP Server environment.
This tool creates a new advertising construct (ad set) within an existing campaign. Ad sets are reversible (can be paused or deleted), so this is Write rather than Destructive. However, severity is high because creating ad sets can commit advertising spend, establish targeting parameters, and affect campaign performance.
From the tool's definition Tool name 'create_ad_set' and description 'Create a new ad set within a campaign' indicate data creation. The Meta Marketing API context shows this manages advertising campaigns with budget/targeting implications.
Attacks that exploit this kind of access
Create a new ad set within a campaign. It is categorised as a Write tool in the Meta Marketing API MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Meta Marketing API MCP Server MCP server in PolicyLayer and add a rule for create_ad_set: 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 Marketing API MCP Server. Nothing to install.
create_ad_set 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 create_ad_set 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 create_ad_set. 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.
create_ad_set is provided by the Meta Marketing API MCP Server MCP server (pythonando/meta-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 →