List announcements. Pass a course_id for one course, or omit it to fetch
AI agents call list_announcements 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 retrieves announcement data from Canvas LMS without any side effects. It follows the Read category pattern (list/fetch operations) consistent with sibling tools like list_courses, list_assignments, list_files, etc. The severity is low because retrieval of course announcements poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'list_announcements' and description 'List announcements' indicate a retrieval operation. Server description states 'Reads live data on every request.' No modification, deletion, or execution capability mentioned.
Attacks that exploit this kind of access
List announcements. Pass a course_id for one course, or omit it to fetch. 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_announcements: 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_announcements 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_announcements 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_announcements. 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_announcements 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 →