AI agents use create_brand_profile to create or update resources in Raven — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Raven environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | — | Optional stable ID. If omitted, Raven creates one from the name. |
name | string | Yes | Brand or project name. |
tone | string | — | Voice and tone guidance. |
fonts | array | — | Brand fonts or type guidance. |
colors | array | — | Brand colors, preferably hex or token names. |
product | string | — | Product or offer notes. |
audience | string | — | Primary audience/customer. |
asset_ids | array | — | Existing Raven creative asset IDs tied to this brand. |
constraints | array | — | Rules to honor: no claims, legal notes, visual constraints. |
description | string | — | What the brand/product is. |
Parameters from the server's own tool schema.
This tool creates or modifies brand profile data, which is reversible and fits the Write category. Severity is medium because: (1) brand profiles influence generated UI output, so corruption could degrade design quality across multiple creative jobs; (2) the data is stored locally and may be relied upon by other Raven tools; (3) however, there is no destruction, financial impact, or code execution.
From the tool's definition Tool description explicitly states it "Create or update a local brand profile" — creates or modifies data. Stores configuration data (colors, fonts, tone, audience, constraints, product notes, asset references) locally under ~/.raven/creative.
Risk signalsHigh parameter count (10 properties)
Attacks that exploit this kind of access
Create or update a local brand profile used by Raven creative jobs. Stores colors, fonts, tone, audience, constraints, product notes, and asset references locally under ~/.raven/creative by default. It is categorised as a Write tool in the Raven MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_brand_profile accepts 10 parameters: id, name, tone, fonts, colors, product, audience, asset_ids, constraints, description. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Raven MCP server in PolicyLayer and add a rule for create_brand_profile: 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 Raven. Nothing to install.
create_brand_profile 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_brand_profile 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_brand_profile. 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_brand_profile is provided by the Raven MCP server (raven-mcp). 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 →