AI agents use draft_create_custom_html_ad_item 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
draft | object | Yes | Object containing custom HTML ad item fields (name, custom_html required) |
campaign_draft_id | number | Yes | Draft campaign ID this ad item belongs to |
Parameters from the server's own tool schema.
This tool creates new data (a custom HTML ad item) but in draft form, which is reversible and modifiable. It does not execute arbitrary code, delete data irreversibly, or move money. The medium severity reflects that malicious actors could create spam/malicious ad items that would require cleanup, but the damage is bounded and reversible by deletion or modification.
From the tool's definition Tool name contains 'create' and description states 'Create a new draft custom HTML ad item'. The draft status and reversible nature (typical ad items can be modified or deleted) indicates write capability rather than destructive.
Attacks that exploit this kind of access
Create a new draft custom HTML ad item. 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.
draft_create_custom_html_ad_item accepts 2 parameters: draft, campaign_draft_id. Required: draft, campaign_draft_id. The full parameter table on this page comes from the server's own tool schema.
Register the AdButler MCP server in PolicyLayer and add a rule for draft_create_custom_html_ad_item: 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.
draft_create_custom_html_ad_item 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 draft_create_custom_html_ad_item 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 draft_create_custom_html_ad_item. 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.
draft_create_custom_html_ad_item 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.
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 →