Retrieve available academic report cards.
AI agents call get_reports to retrieve information from Smartschool MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing academic report data without any side effects. It is a straightforward read operation similar to sibling tools like get_results, get_messages, and get_schedule. The blast radius of misuse is minimal since it only exposes information the authenticated user would normally have access to within their school account.
From the tool's definition Tool name is 'get_reports' and description states 'Retrieve available academic report cards' — purely a data retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Retrieve available academic report cards. It is categorised as a Read tool in the Smartschool MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Smartschool MCP Server MCP server in PolicyLayer and add a rule for get_reports: 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 Smartschool MCP Server. Nothing to install.
get_reports 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_reports 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_reports. 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_reports is provided by the Smartschool MCP Server MCP server (maurodruwel/smartschool-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 →