create_lookalike_audience

WHAT IT DOES

What create_lookalike_audience does on Meta Marketing API MCP Server

AI agents use create_lookalike_audience 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.

WHY IT NEEDS A POLICY

Why create_lookalike_audience needs a policy

This tool creates new audience segments (lookalike audiences) which is a reversible data creation operation. While this could be misused to target unintended demographics at scale, causing financial waste or reaching wrong audiences, the operation itself is a Write action (create) rather than Destructive (irreversible deletion) or Financial (direct payment movement).

From the tool's definition Tool name 'create_lookalike_audience' and description 'Create a lookalike audience based on a source audience' indicate the tool creates new audience data within the Meta advertising platform. This is a write operation that modifies advertising infrastructure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_lookalike_audience Rate-limited

create_lookalike_audience stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_lookalike_audience": {
      "limits": [
        {
          "counter": "create_lookalike_audience_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Meta Marketing API MCP Server, so you can run agents against it safely.

FAQ

Questions about create_lookalike_audience

What does the create_lookalike_audience tool do? +

Create a lookalike audience based on a source audience. 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.

How do I enforce a policy on create_lookalike_audience? +

Register the Meta Marketing API MCP Server MCP server in PolicyLayer and add a rule for create_lookalike_audience: 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.

What risk level is create_lookalike_audience? +

create_lookalike_audience is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_lookalike_audience? +

Yes. Add a rate_limit block to the create_lookalike_audience 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.

How do I block create_lookalike_audience completely? +

Set action: deny in the PolicyLayer policy for create_lookalike_audience. 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.

What MCP server provides create_lookalike_audience? +

create_lookalike_audience 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.