AI agents use create_character to create or update resources in Narrarium — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Narrarium environment.
This tool creates character files within a local Narrarium book repository system. This is a reversible write operation—character files can be modified or removed later. The blast radius is low because it only adds structured character data to a creative writing system with no side effects on external systems, financial implications, or irreversible destruction.
From the tool's definition Tool description states 'Create a rich character file' - this is creating new data in the book repository system. The term 'Create' combined with 'character file' indicates data creation rather than retrieval or deletion.
Attacks that exploit this kind of access
Create a rich character file using the Narrarium character wizard fields. Use this instead of the generic entity tool when the user is adding a real story character. It is categorised as a Write tool in the Narrarium MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Narrarium MCP server in PolicyLayer and add a rule for 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 Narrarium. Nothing to install.
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 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 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.
create_character is provided by the Narrarium MCP server (narrarium-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 →