List assignments for a course, including the student
AI agents call list_assignments 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 retrieves assignment data from Canvas LMS without modifying, deleting, or executing any operations. It has no side effects and poses minimal security risk—the blast radius of misuse is limited to unauthorized information disclosure of academic assignment data, which is lower severity than write, execute, or destructive operations.
From the tool's definition Tool name 'list_assignments' and description 'List assignments for a course' indicate a retrieval operation. The server description states 'Reads live data on every request' and the sibling tools (get_*, list_*) are all read-only queries.
Attacks that exploit this kind of access
List assignments for a course, including the student. 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_assignments: 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_assignments 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_assignments 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_assignments. 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_assignments 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 →