clone_questionary · Yanifend MCP: Risk & Policy

WHAT IT DOES

What clone_questionary does on Yanifend

AI agents use clone_questionary to create or update resources in Yanifend — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yanifend environment.

WHY IT NEEDS A POLICY

Why clone_questionary needs a policy

The tool duplicates/copies existing questions and options, creating new data in the system. This is a write/create operation (reversible - the copies can be deleted), not destructive. The blast radius is medium since it could create a large number of duplicate records across the entire questionary.

From the tool's definition Copy ALL questions + options from one personage

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

clone_questionary Rate-limited

clone_questionary 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": {
    "clone_questionary": {
      "limits": [
        {
          "counter": "clone_questionary_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 Yanifend, so you can run agents against it safely.

FAQ

Questions about clone_questionary

What does the clone_questionary tool do? +

Copy ALL questions + options from one personage. It is categorised as a Write tool in the Yanifend MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on clone_questionary? +

Register the Yanifend MCP server in PolicyLayer and add a rule for clone_questionary: 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 Yanifend. Nothing to install.

What risk level is clone_questionary? +

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

Can I rate-limit clone_questionary? +

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

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

clone_questionary is provided by the Yanifend MCP server (skippedaga/yanifend-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.