AI agents call canvas_list_announcements to retrieve information from Canvas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool gathers and returns announcement data without creating, modifying, or deleting any information. It is a straightforward data retrieval operation consistent with the 'Read' category. Severity is low because announcements are generally non-sensitive informational content in an LMS context, and read access poses minimal risk to the system or users.
From the tool's definition Tool retrieves 'Recent announcements' with optional filtering by course_id. This is a read-only query operation with no side effects.
Attacks that exploit this kind of access
Recent announcements. Omit course_id to gather announcements across all active courses, or pass a. It is categorised as a Read tool in the Canvas MCP Server, which means it retrieves data without modifying state.
Register the Canvas MCP server in PolicyLayer and add a rule for canvas_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 Canvas. Nothing to install.
canvas_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 canvas_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 canvas_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.
canvas_list_announcements 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 →