query_group_tasks
AI agents call query_group_tasks to retrieve information from Xiaoya Teacher without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates a query operation on group/class tasks, which is a retrieval action with no side effects. Even though the description is empty, the naming pattern 'query_*' combined with the server's documented 'batch_query' and '班级查询' (class query) capabilities confirms this is a Read operation that retrieves task information for educational groups/classes.
From the tool's definition Tool name 'query_group_tasks' follows the 'query_*' pattern, which typically retrieves or lists data. The server description indicates 'batch查询' (batch query) and '班级查询' (class/group query) are read operations.
Attacks that exploit this kind of access
query_group_tasks. It is categorised as a Read tool in the Xiaoya Teacher MCP Server, which means it retrieves data without modifying state.
Register the Xiaoya Teacher MCP server in PolicyLayer and add a rule for query_group_tasks: 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 Xiaoya Teacher. Nothing to install.
query_group_tasks 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 query_group_tasks 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 query_group_tasks. 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.
query_group_tasks is provided by the Xiaoya Teacher MCP server (sav1our520/xiaoya-teacher-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 →