AI agents use archivar_curso to create or update resources in Moodle — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Moodle environment.
Although archiving changes course visibility and affects user access (teacher access intact but course hidden from students), it is explicitly non-destructive and fully reversible (un-archive restores visibility). This makes it Write rather than Destructive.
From the tool's definition The tool description states it can 'Archive (visible=0) or un-archive (visible=1) a course' and explicitly notes 'Non-destructive: data, enrolments and teacher access stay intact.' This describes a reversible modification of course visibility state.
Attacks that exploit this kind of access
Archive (visible=0) or un-archive (visible=1) a course. Non-destructive: data, enrolments and teacher access stay intact. Use it for end-of-year cleanup or hiding a course in preparation. It is categorised as a Write tool in the Moodle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Moodle MCP server in PolicyLayer and add a rule for archivar_curso: 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 Moodle. Nothing to install.
archivar_curso is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the archivar_curso 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 archivar_curso. 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.
archivar_curso is provided by the Moodle MCP server (marcosnahuel/moodle-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 →