create_persona · Narrarium MCP: Risk & Policy

WHAT IT DOES

What create_persona does on Narrarium

AI agents use create_persona 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.

WHY IT NEEDS A POLICY

Why create_persona needs a policy

This tool creates a new data file (persona) in the repository, which is a reversible write operation. The data being created is non-sensitive metadata about fictional reader archetypes for narrative review purposes. It has no destructive, financial, or execute-like effects, and does not retrieve existing data. The blast radius of misuse is minimal—creating unwanted personas can be easily deleted or overwritten.

From the tool's definition Create a reader persona file in personas/ of the book repository.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_persona Rate-limited

create_persona stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_persona": {
      "limits": [
        {
          "counter": "create_persona_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Narrarium, so you can run agents against it safely.

FAQ

Questions about create_persona

What does the create_persona tool do? +

Create a reader persona file in personas/ of the book repository. Personas represent fictional reader archetypes used to review chapters from different perspectives. Each persona has reading habits, values, dislikes, beauty and readability focus areas, emotional triggers, and tolerance scores. Use seed_default_personas to populate the book with the five built-in archetypes instead of creating one manually. 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.

How do I enforce a policy on create_persona? +

Register the Narrarium MCP server in PolicyLayer and add a rule for create_persona: 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.

What risk level is create_persona? +

create_persona is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_persona? +

Yes. Add a rate_limit block to the create_persona 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.

How do I block create_persona completely? +

Set action: deny in the PolicyLayer policy for create_persona. 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.

What MCP server provides create_persona? +

create_persona 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.