AI agents use create_custom_report 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 |
|---|---|---|---|
date | object | Yes | Date configuration (either preset or start+end required) |
name | string | Yes | Report name |
type | string | Yes | Report type |
period | string | Yes | Data grouping period |
columns | array | — | Columns to include: impressions, eligible, viewable, clicks, conversions, ctr, cvr, e_cpm, e_cpc, e_cpa, cost, payout, revenue |
filters | object | — | Filter criteria: { publishers: [...], advertisers: [...], zones: [...], campaigns: [...], ad_items: [...], channels: [...] } |
exclude_channel_stats | boolean | — | Exclude stats from channel-served ads |
require_channel_stats | boolean | — | Only include stats from channel-served ads |
exclude_campaign_ad_items | boolean | — | Exclude ad items in campaigns |
exclude_publisher_ad_items | boolean | — | Exclude ad items directly in zones |
Parameters from the server's own tool schema.
The tool creates new data (a report configuration) but does not execute code, delete data irreversibly, move money, or trigger external operations with unpredictable effects. Creating a report configuration is a standard Write operation—reversible through deletion or modification. Severity is low because report configurations are non-critical metadata with limited blast radius if misused.
From the tool's definition Tool name 'create_custom_report' and description 'Create a new report configuration' indicate a reversible creation action that adds a new reporting configuration to the AdButler system.
Risk signalsHigh parameter count (14 properties)
Attacks that exploit this kind of access
Create a new report configuration. 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.
create_custom_report accepts 10 parameters: date, name, type, period, columns, filters, exclude_channel_stats, require_channel_stats, exclude_campaign_ad_items, exclude_publisher_ad_items. Required: date, name, type, period. 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 create_custom_report: 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.
create_custom_report 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_custom_report 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_custom_report. 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_custom_report 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 →