List quizzes for a course (title, due date, points, question count, attempts). Requires course_id.
AI agents call list_quizzes to retrieve information from PokeCanvas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns structured data about quizzes without creating, modifying, deleting, or executing any operations. It is a pure retrieval operation consistent with Read category. Severity is low because the blast radius of misuse is limited to unauthorized information access about course assessments, which is already available to enrolled students in most LMS contexts.
From the tool's definition Tool 'list_quizzes' retrieves quiz metadata (title, due date, points, question count, attempts) with no modification capability.
Attacks that exploit this kind of access
List quizzes for a course (title, due date, points, question count, attempts). Requires course_id. It is categorised as a Read tool in the PokeCanvas MCP Server, which means it retrieves data without modifying state.
Register the PokeCanvas MCP server in PolicyLayer and add a rule for list_quizzes: 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 PokeCanvas. Nothing to install.
list_quizzes 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 list_quizzes 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 list_quizzes. 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.
list_quizzes is provided by the PokeCanvas MCP server (jackulau/pokecanvas). 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 →