Delete a grade.
AI agents call delete_grade to permanently remove resources in Eduframe — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a grade permanently removes academic record data that cannot be recovered through normal means. This is irreversible and falls under the Destructive category. While the blast radius is constrained to a single grade record (not a wholesale purge of all data), the action is definitive and unrecoverable, meriting 'high' severity in an educational context where grades are critical institutional records.
From the tool's definition Tool name is 'delete_grade' with description 'Delete a grade.' The verb 'delete' combined with the explicit action of removing grade records indicates irreversible data deletion.
Attacks that exploit this kind of access
Delete a grade. It is categorised as a Destructive tool in the Eduframe MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Eduframe MCP server in PolicyLayer and add a rule for delete_grade: 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 Eduframe. Nothing to install.
delete_grade is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_grade 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 delete_grade. 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.
delete_grade is provided by the Eduframe MCP server (martijnpieters/eduframe-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 →