query_paper_summary
AI agents call query_paper_summary 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 'query_' prefix strongly suggests a read operation that retrieves information without side effects. While the empty description limits confidence, the naming convention and surrounding tools (which include write/execute operations like 'batch_create_questions', 'configure_paper_basics') indicate this is a simple retrieval tool. Low severity is appropriate for a read-only query operation.
From the tool's definition Tool name 'query_paper_summary' uses the verb 'query', which indicates data retrieval. No description is provided to suggest modification or deletion.
Attacks that exploit this kind of access
query_paper_summary. 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_paper_summary: 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_paper_summary 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_paper_summary 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_paper_summary. 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_paper_summary 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 →