wizard_finalize · Narrarium MCP: Risk & Policy

WHAT IT DOES

What wizard_finalize does on Narrarium

AI agents use wizard_finalize 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 wizard_finalize needs a policy

The tool writes files or folders to a local repository, creating or modifying content. This is a Write operation as it creates/saves data to the filesystem. While it could overwrite existing files, the description doesn't explicitly indicate irreversible deletion, so Destructive is not clearly applicable.

From the tool's definition Finalize a wizard session and write the corresponding file or folder into the local book repository

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wizard_finalize Rate-limited

wizard_finalize 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": {
    "wizard_finalize": {
      "limits": [
        {
          "counter": "wizard_finalize_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 wizard_finalize

What does the wizard_finalize tool do? +

Finalize a wizard session and write the corresponding file or folder into the local book repository. 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 wizard_finalize? +

Register the Narrarium MCP server in PolicyLayer and add a rule for wizard_finalize: 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 wizard_finalize? +

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

Can I rate-limit wizard_finalize? +

Yes. Add a rate_limit block to the wizard_finalize 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 wizard_finalize completely? +

Set action: deny in the PolicyLayer policy for wizard_finalize. 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 wizard_finalize? +

wizard_finalize 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.