AI agents call get_student_info to retrieve information from Qldt Hanu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves student information without creating, modifying, deleting, executing code, or moving money. It is a straightforward data query operation with no side effects. The low severity reflects minimal blast radius—an AI agent misuse would only expose already-accessible student records to the requester.
From the tool's definition Tool name 'get_student_info' and description 'Get student information' indicate retrieval of data with no modification capability. The requirement to be logged in first is a security prerequisite, not a functional modifier.
Attacks that exploit this kind of access
Get student information. MUST BE LOGGED IN FIRST. It is categorised as a Read tool in the Qldt Hanu MCP Server, which means it retrieves data without modifying state.
Register the Qldt Hanu MCP server in PolicyLayer and add a rule for get_student_info: 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 Qldt Hanu. Nothing to install.
get_student_info 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_student_info 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_student_info. 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_student_info is provided by the Qldt Hanu MCP server (qxbao/qldt-hanu-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 →