create_exam · Leafeep MCP: Risk & Policy

WHAT IT DOES

What create_exam does on Leafeep

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

WHY IT NEEDS A POLICY

Why create_exam needs a policy

This tool creates new exam data and associated artifacts (student links, QR codes) but does not execute code, run queries, delete data, or move money. It is a reversible write operation — exams can be modified or closed without permanent consequence.

From the tool's definition Tool description explicitly states 'Create a question set and generate a student link + QR code.' The verb 'Create' indicates data creation. The tool generates new resources (exams, links, QR codes) that persist in the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_exam Rate-limited

create_exam 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_exam": {
      "limits": [
        {
          "counter": "create_exam_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 Leafeep, so you can run agents against it safely.

FAQ

Questions about create_exam

What does the create_exam tool do? +

Create a question set and generate a student link + QR code. It is categorised as a Write tool in the Leafeep 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_exam? +

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

What risk level is create_exam? +

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

Can I rate-limit create_exam? +

Yes. Add a rate_limit block to the create_exam 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_exam completely? +

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

create_exam is provided by the Leafeep MCP server (xhae123/leafeep-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.