Create a local character/identity reference profile for consistent image or video generation. Raven stores reference asset IDs and provider-training payloads; actual identity training happens only through a configured provider runner.
AI agents use create_character_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. |
name | string | Yes | Character, spokesperson, founder, avatar, or product persona name. |
metadata | object | — | Optional non-secret metadata. |
description | string | — | Visual/personality description. |
consistency_notes | string | — | What must stay consistent across generations. |
reference_asset_ids | array | Yes | Raven creative asset IDs for reference images/videos. |
provider_training_id | string | — | External provider training/character ID if already trained. |
Parameters from the server's own tool schema.
The tool creates new profiles and stores data (asset IDs, training payloads) in a local system. This is a reversible write operation: profiles can be updated or deleted. It does not delete data (not Destructive), execute arbitrary code (not Execute), move money (not Financial), or trigger irreversible external side effects.
From the tool's definition Tool description states 'Create a local character/identity reference profile' and 'stores reference asset IDs and provider-training payloads' — explicitly creates and modifies data.
Attacks that exploit this kind of access
Create a local character/identity reference profile for consistent image or video generation. Raven stores reference asset IDs and provider-training payloads; actual identity training happens only through a configured provider runner. 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_character_profile accepts 7 parameters: id, name, metadata, description, consistency_notes, reference_asset_ids, provider_training_id. Required: name, reference_asset_ids. 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_character_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_character_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_character_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_character_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_character_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 →