AI agents use canvas_submit_assignment to create or update resources in Canvas — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Canvas environment.
This tool creates new submission records or updates existing ones in an educational system, which is a reversible write operation. It has high severity because submission actions directly affect a student's academic standing and grade calculations—misuse could result in unauthorized submissions, cheating, or unintended grade impacts.
From the tool's definition The tool performs a 'submit work to an assignment' action, which creates or modifies submission data in Canvas.
Attacks that exploit this kind of access
Submit work to an assignment as a text entry, a URL, or an uploaded local file. It is categorised as a Write tool in the Canvas MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Canvas MCP server in PolicyLayer and add a rule for canvas_submit_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. Nothing to install.
canvas_submit_assignment is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the canvas_submit_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 canvas_submit_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.
canvas_submit_assignment is provided by the Canvas MCP server (tylergibbs1/canvas-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 →