submit_question · QMYZ- MCP: Risk & Policy

WHAT IT DOES

What submit_question does on QMYZ-MCP

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

WHY IT NEEDS A POLICY

Why submit_question needs a policy

This tool creates or records quiz answer submissions on the Qingma Yizhan platform. While submissions may theoretically be editable, they represent state changes to an educational assessment system. The tool is Write rather than Execute because it doesn't run arbitrary code—it performs a specific, bounded operation (answer submission).

From the tool's definition Tool name 'submit_question' and description '提交课程题目答案, 返回答题结果' (submit course question answers, return answering results).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

submit_question Rate-limited

submit_question 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": {
    "submit_question": {
      "limits": [
        {
          "counter": "submit_question_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 QMYZ-MCP, so you can run agents against it safely.

FAQ

Questions about submit_question

What does the submit_question tool do? +

提交课程题目答案, 返回答题结果。提交的answer应为选项的字母，例如 "A" 或 "B". It is categorised as a Write tool in the QMYZ-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on submit_question? +

Register the QMYZ- MCP server in PolicyLayer and add a rule for submit_question: 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 QMYZ-MCP. Nothing to install.

What risk level is submit_question? +

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

Can I rate-limit submit_question? +

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

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

submit_question is provided by the QMYZ- MCP server (shibig666/qmyz-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.