Get detailed assignment-level data for a specific course. Returns every assignment with its score, points possible, due date, and type. Use this to deeply analyze a single class.
AI agents call get_grade_details 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 queries and displays existing school data (assignments, scores, dates) without creating, modifying, deleting, or executing any actions. The stated purpose is to 'deeply analyze a single class,' which is introspection. No financial, destructive, or side-effect operations are possible. Classification as Read is appropriate with high confidence.
From the tool's definition Tool retrieves 'detailed assignment-level data' with 'score, points possible, due date, and type' — a pure query operation with 'no side effects' per the tool description. Verbs like 'Get' and 'Returns' indicate data retrieval only.
Attacks that exploit this kind of access
Get detailed assignment-level data for a specific course. Returns every assignment with its score, points possible, due date, and type. Use this to deeply analyze a single class. 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_grade_details: 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_grade_details 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_grade_details 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_grade_details. 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_grade_details 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 →