Get the student\
AI agents call get_student_info to retrieve information from School MCP 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 from StudentVue dashboards without modifying, deleting, or executing external operations. Even if it fetches PII, the classification is determined by the action (retrieval) not the sensitivity of data. Blast radius is minimal—misuse would expose student data but cannot alter it or trigger financial/destructive actions.
From the tool's definition Tool name 'get_student_info' and server context describing 'queries about grades, GPA, attendance, and schedules' indicates data retrieval.
Attacks that exploit this kind of access
Get the student\. It is categorised as a Read tool in the School MCP MCP Server, which means it retrieves data without modifying state.
Register the School 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 School MCP. 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 School MCP server (shengdynasty/school-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_student_info is one line of School's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →