wizard_answer · Narrarium MCP: Risk & Policy

WHAT IT DOES

What wizard_answer does on Narrarium

AI agents use wizard_answer 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_answer needs a policy

The tool modifies state by recording answers in an ongoing wizard session, progressing through a guided creation flow. This is Write-category (creates or modifies data reversibly) rather than Read since it's not merely retrieving data but accepting and storing user inputs that advance a creative workflow.

From the tool's definition Tool description states it 'Answer the current prompt in a running wizard session and receive the next guided question.' This indicates the tool processes user input (writes/records answers) within an interactive wizard workflow that guides through creation…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wizard_answer Rate-limited

wizard_answer 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_answer": {
      "limits": [
        {
          "counter": "wizard_answer_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_answer

What does the wizard_answer tool do? +

Answer the current prompt in a running wizard session and receive the next guided question. 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_answer? +

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

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

Can I rate-limit wizard_answer? +

Yes. Add a rate_limit block to the wizard_answer 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_answer completely? +

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

wizard_answer 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.