Delete (archive) an assignment from a course.
AI agents call delete-assignment to permanently remove resources in Canvas MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes an assignment, which is a critical course component that students rely on. While described as 'archive,' deletion of educational material affects multiple stakeholders (students, instructors) and their records. Misuse by an AI agent could remove important assignments, disrupt coursework, and cause significant operational disruption in a learning management system.
From the tool's definition Tool name is 'delete-assignment' and description states 'Delete (archive) an assignment from a course.' The verb 'delete' combined with the action of removing an assignment from an educational platform represents an irreversible or difficult-to-undo action.
Documented attack patterns abuse exactly the kind of access delete-assignment gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Canvas MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete-assignment:
{
"version": "1",
"default": "deny",
"hide": [
"delete-assignment"
]
}delete-assignment disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete (archive) an assignment from a course. It is categorised as a Destructive tool in the Canvas MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Canvas MCP Server MCP server in PolicyLayer and add a rule for delete-assignment: 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 Canvas MCP Server. Nothing to install.
delete-assignment 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-assignment 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-assignment. 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-assignment is provided by the Canvas MCP Server MCP server (r-huijts/canvas-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Canvas MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
50 Canvas MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.