AI agents use openart_create_character to create or update resources in Openart — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openart environment.
This tool creates and stores new data (a character profile) on OpenArt.ai. Creation operations are reversible (the character can typically be deleted), so this falls under Write rather than Destructive.
From the tool's definition Tool description states 'Create a new OpenArt character', which is a create operation that adds new data to the OpenArt.ai platform. The tool accepts parameters (name, image path, background story, voice ID) to construct and persist a new character resource.
Attacks that exploit this kind of access
Create a new OpenArt character from an image. Provide name, local image path, optional background story, optional voice ID. It is categorised as a Write tool in the Openart MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openart MCP server in PolicyLayer and add a rule for openart_create_character: 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 Openart. Nothing to install.
openart_create_character 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 openart_create_character 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 openart_create_character. 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.
openart_create_character is provided by the Openart MCP server (jbertus/openart-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 →