This record as markdown: /tools/54yyyu-school-mcp/list-courses.md
What list_courses does on School MCP
AI agents call list_courses to retrieve information from School MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_courses is rated Low
This tool retrieves a list of courses from Canvas, a read-only operation with no data modification, execution of code, deletion, or financial implications. The blast radius is minimal—an AI agent could at worst enumerate courses already accessible to the authenticated user. Severity is low because the information returned is likely limited to courses the user is already enrolled in or has access to.
From the tool's definition Tool name 'list_courses' and description 'List available courses from Canvas' indicate a query operation that retrieves course data without modification or side effects.
Attacks that exploit this kind of access
The rule that runs list_courses safely
PolicyLayer is an MCP gateway: it sits between your AI agents and School MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_courses, this is the rule to start with:
list_courses is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect School MCP, apply this rule, and every list_courses call is checked against it from then on.
Questions about list_courses
List available courses from Canvas. It is categorised as a Read tool in the School MCP MCP Server, which means it retrieves data without modifying state.
Register the School MCP server in PolicyLayer and add a rule for list_courses: 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 School MCP. Nothing to install.
list_courses 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_courses 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_courses. 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_courses is provided by the School MCP server (54yyyu/school-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on School, and thousands of servers like it.
This server
Across the catalogue