Obtiene los anuncios de una materia. Requiere course_id.
AI agents call announcements to retrieve information from Canvas MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves announcements from a Canvas course, which is a read-only operation that queries existing data without creating, modifying, deleting, or executing actions. It has minimal blast radius as misuse would only expose information the user likely already has access to within their course.
From the tool's definition Tool name 'announcements' and description 'Obtiene los anuncios de una materia' (Gets the announcements of a subject) with required course_id parameter. The verb 'obtiene' (gets/retrieves) indicates data retrieval with no modification.
Attacks that exploit this kind of access
Obtiene los anuncios de una materia. Requiere course_id. It is categorised as a Read tool in the Canvas MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Canvas MCP Server MCP server in PolicyLayer and add a rule for 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 MCP Server. Nothing to install.
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 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 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.
announcements is provided by the Canvas MCP Server MCP server (the-greenpanter/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 →