update_audience · AdButler MCP: Risk & Policy

WHAT IT DOES

What update_audience does on AdButler

AI agents use update_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
`id`	number	Yes	Audience ID
`name`	string	—	Audience name
`attributes`	object	—	Attribute targets defining the audience
`user_db_id`	number	Yes	User database ID

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why update_audience needs a policy

This tool modifies existing data (audience records) in a database. It is reversible (can be updated again), so it falls under Write rather than Destructive. The severity is medium because unintended modifications to audience targeting data could affect advertising campaigns and user segmentation, but the impact is not catastrophic or irreversible.

From the tool's definition The tool name is 'update_audience' and description states it 'Update an existing audience in a user database'. The verb 'update' explicitly indicates modification of data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_audience Rate-limited

update_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": {
    "update_audience": {
      "limits": [
        {
          "counter": "update_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 update_audience

What does the update_audience tool do? +

Update an existing 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 update_audience accept? +

update_audience accepts 4 parameters: id, name, attributes, user_db_id. Required: id, 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 update_audience? +

Register the AdButler MCP server in PolicyLayer and add a rule for update_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 update_audience? +

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

Can I rate-limit update_audience? +

Yes. Add a rate_limit block to the update_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 update_audience completely? +

Set action: deny in the PolicyLayer policy for update_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 update_audience? +

update_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.