Get the student\
AI agents call get_attendance 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 attendance information from a StudentVue dashboard. It is a read-only query operation that pulls existing data without side effects, modification, or triggering external operations. The 'get_*' naming convention confirms it is a data retrieval tool. No evidence suggests it can modify records, execute commands, or cause financial impact.
From the tool's definition Tool name 'get_attendance' and the pattern of sibling tools (get_assignments_due, get_calendar, get_grade_summary, get_gpa) all follow a 'get_*' retrieval pattern.
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_attendance: 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_attendance 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_attendance 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_attendance. 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_attendance 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.
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 →