canvas_start_quiz_attempt
Start a new quiz attempt. Returns a quiz_submission object with
This record as markdown: /tools/cowork-bench/canvas-start-quiz-attempt.md
What canvas_start_quiz_attempt does on Cowork Bench
AI agents use canvas_start_quiz_attempt to create or update resources in Cowork Bench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cowork Bench environment.
Why canvas_start_quiz_attempt is rated Medium
This tool creates a new quiz attempt/submission record in Canvas LMS. It is a Write operation as it creates new data (a quiz_submission object) reversibly. Severity is medium because misuse could create spurious quiz attempts affecting academic records, but it is not irreversible or financial.
From the tool's definition 'Start a new quiz attempt' and 'Returns a quiz_submission object'
Attacks that exploit this kind of access
The rule that runs canvas_start_quiz_attempt safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For canvas_start_quiz_attempt, this is the rule to start with:
canvas_start_quiz_attempt stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every canvas_start_quiz_attempt call is checked against it from then on.
Questions about canvas_start_quiz_attempt
Start a new quiz attempt. Returns a quiz_submission object with. It is categorised as a Write tool in the Cowork Bench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for canvas_start_quiz_attempt: 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 Cowork Bench. Nothing to install.
canvas_start_quiz_attempt 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_start_quiz_attempt 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_start_quiz_attempt. 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_start_quiz_attempt is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
This server
Across the catalogue