# create_role

Create a new role with permission settings

Agent View of the PolicyLayer registry record for `create_role`. HTML page: https://policylayer.com/tools/adbutler/create-role

## Facts

- Tool: `create_role`
- Server: AdButler (`adbutler/mcp-server`) — https://policylayer.com/tools/adbutler.md
- Homepage: https://github.com/adbutler/mcp-server
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 12 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `name` | string | yes | Role name |
| `is_default_role` | boolean | no | Auto-assign this role to new users |
| `can_manage_links` | boolean | no | Can manage tracking links |
| `can_manage_media` | boolean | no | Can manage creatives and media groups |
| `can_manage_users` | boolean | no | Can manage users |
| `publisher_access` | string | no | Publisher access level |
| `statistics_access` | string | no | Statistics access level |
| `can_manage_bidders` | boolean | no | Can manage bidders |
| `can_manage_billing` | boolean | no | Can manage billing |
| `can_manage_targets` | boolean | no | Can manage targets |
| `can_manage_tickets` | boolean | no | Can manage tickets |
| `can_manage_contracts` | boolean | no | Can manage contracts |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_role",
    "arguments": {
      "name": "<name>"
    }
  }
}
```

## Why create_role is rated Medium

This tool creates new roles (a reversible operation), which modifies the system's access control configuration. While not deleting or executing arbitrary code, creating roles with permission settings can expand access and affect system security posture if misused by an AI agent (e.g., creating overly permissive roles).

From the tool's own definition: "Tool name 'create_role' and description 'Create a new role with permission settings' indicate this creates a new administrative entity with access control implications."

Risk signals: High parameter count (20 properties)

## Use case

AI agents use create_role 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches AdButler:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_role": {
      "limits": [
        {
          "counter": "create_role_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on AdButler (621)

- `archive_advertiser` — Destructive — https://policylayer.com/tools/adbutler/archive-advertiser.md
- `archive_channel` — Destructive — https://policylayer.com/tools/adbutler/archive-channel.md
- `archive_contract` — Destructive — https://policylayer.com/tools/adbutler/archive-contract.md
- `archive_email_zone` — Destructive — https://policylayer.com/tools/adbutler/archive-email-zone.md
- `archive_publisher` — Destructive — https://policylayer.com/tools/adbutler/archive-publisher.md
- `bulk_upload_remove_data_list` — Destructive — https://policylayer.com/tools/adbutler/bulk-upload-remove-data-list.md
- `bulk_upload_replace_user_db` — Destructive — https://policylayer.com/tools/adbutler/bulk-upload-replace-user-db.md
- `campaign_bulk_delete_catalog_ad_items` — Destructive — https://policylayer.com/tools/adbutler/campaign-bulk-delete-catalog-ad-items.md
- `cancel_signature_request` — Destructive — https://policylayer.com/tools/adbutler/cancel-signature-request.md
- `delete_advertiser` — Destructive — https://policylayer.com/tools/adbutler/delete-advertiser.md
- `delete_archived_campaign` — Destructive — https://policylayer.com/tools/adbutler/delete-archived-campaign.md
- `delete_archived_channel` — Destructive — https://policylayer.com/tools/adbutler/delete-archived-channel.md
- `delete_archived_contract` — Destructive — https://policylayer.com/tools/adbutler/delete-archived-contract.md
- `delete_audience` — Destructive — https://policylayer.com/tools/adbutler/delete-audience.md
- `delete_audio_creative` — Destructive — https://policylayer.com/tools/adbutler/delete-audio-creative.md
- `delete_beacon_signing_key` — Destructive — https://policylayer.com/tools/adbutler/delete-beacon-signing-key.md
- `delete_bidder` — Destructive — https://policylayer.com/tools/adbutler/delete-bidder.md
- `delete_campaign` — Destructive — https://policylayer.com/tools/adbutler/delete-campaign.md
- `delete_campaign_assignment` — Destructive — https://policylayer.com/tools/adbutler/delete-campaign-assignment.md
- `delete_catalog_ad_item` — Destructive — https://policylayer.com/tools/adbutler/delete-catalog-ad-item.md
- `delete_catalog_zone` — Destructive — https://policylayer.com/tools/adbutler/delete-catalog-zone.md
- `delete_channel` — Destructive — https://policylayer.com/tools/adbutler/delete-channel.md
- `delete_channel_zone_assignment` — Destructive — https://policylayer.com/tools/adbutler/delete-channel-zone-assignment.md
- `delete_contact` — Destructive — https://policylayer.com/tools/adbutler/delete-contact.md
- `delete_contract` — Destructive — https://policylayer.com/tools/adbutler/delete-contract.md
- `delete_contract_document` — Destructive — https://policylayer.com/tools/adbutler/delete-contract-document.md
- `delete_contract_payment` — Destructive — https://policylayer.com/tools/adbutler/delete-contract-payment.md
- `delete_contract_template` — Destructive — https://policylayer.com/tools/adbutler/delete-contract-template.md
- `delete_creative` — Destructive — https://policylayer.com/tools/adbutler/delete-creative.md
- `delete_custom_html_ad_item` — Destructive — https://policylayer.com/tools/adbutler/delete-custom-html-ad-item.md
- …and 591 more: https://policylayer.com/tools/adbutler.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=adbutler · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/adbutler