create_audience · AdButler MCP: Risk & Policy

WHAT IT DOES

What create_audience does on AdButler

AI agents use create_audience to create or update resources in AdButler — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AdButler environment.

PARAMETERS

Parameter	Type	Required	Description
`name`	string	—	Audience name
`attributes`	object	—	Attribute targets defining the audience (e.g. { "gender": { "operator": "=", "operand": "male" } })
`user_db_id`	number	Yes	User database ID

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why create_audience needs a policy

This tool creates a new audience record in a user database, which is a reversible write operation. It modifies database state but does not delete, execute arbitrary code, or commit financial transactions. The severity is medium because uncontrolled audience creation could lead to data bloat or incorrect targeting in ad campaigns, but the impact is bounded and reversible.

From the tool's definition Tool name 'create_audience' and description 'Create a new audience in a user database' indicate data creation/modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_audience Rate-limited

create_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_audience": {
      "limits": [
        {
          "counter": "create_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 AdButler, so you can run agents against it safely.

FAQ

Questions about create_audience

What does the create_audience tool do? +

Create a new audience in a user database. It is categorised as a Write tool in the AdButler MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does create_audience accept? +

create_audience accepts 3 parameters: name, attributes, user_db_id. Required: user_db_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_audience? +

Register the AdButler MCP server in PolicyLayer and add a rule for create_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 AdButler. Nothing to install.

What risk level is create_audience? +

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

Can I rate-limit create_audience? +

Yes. Add a rate_limit block to the create_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_audience completely? +

Set action: deny in the PolicyLayer policy for create_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_audience? +

create_audience is provided by the AdButler MCP server (adbutler/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.