AI agents call get_question to retrieve information from QMYZ-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves question details from the Qingma Yizhan platform. It performs a read-only query operation to fetch course content without creating, modifying, deleting, or executing any actions.
From the tool's definition Tool name 'get_question' and description '获取课程题目' (fetch course questions) indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
获取课程题目. It is categorised as a Read tool in the QMYZ-MCP MCP Server, which means it retrieves data without modifying state.
Register the QMYZ- MCP server in PolicyLayer and add a rule for get_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.
get_question is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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.
Set action: deny in the PolicyLayer policy for get_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.
get_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →