Lấy câu hỏi dẫn dắt hội thoại cho một chủ đề.
AI agents call get_guiding_questions to retrieve information from MCP English Tutor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves guiding questions for conversational practice—a pure read operation with no side effects. It fits the 'Read' category: it searches or fetches data (conversation prompts) to support tutoring workflows. The severity is low because misuse poses minimal risk: an AI providing wrong or inappropriate guiding questions causes no damage, data loss, or financial harm.
From the tool's definition Tool description translates to 'Get guiding questions for a conversation on a topic' — a retrieval operation.
Attacks that exploit this kind of access
Lấy câu hỏi dẫn dắt hội thoại cho một chủ đề. It is categorised as a Read tool in the MCP English Tutor MCP Server, which means it retrieves data without modifying state.
Register the MCP English Tutor MCP server in PolicyLayer and add a rule for get_guiding_questions: 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 MCP English Tutor. Nothing to install.
get_guiding_questions 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_guiding_questions 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_guiding_questions. 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_guiding_questions is provided by the MCP English Tutor MCP server (thanhlong27042003/mcp-server). 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 →