AI agents use dar_baja 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.
The tool modifies course enrollment status for users, which is a Write operation as it changes data state reversibly. While unenrollment could be sensitive in an educational context, it is explicitly non-destructive and can be reversed by re-enrolling users.
From the tool's definition Tool description states it 'Unenrol one or more users from a course' and explicitly notes 'user data is preserved, only the course enrolment link is removed.' This is a reversible modification operation.
Attacks that exploit this kind of access
Unenrol one or more users from a course. Non-destructive: user data is preserved, only the course enrolment link is removed. 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 dar_baja: 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.
dar_baja 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 dar_baja 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 dar_baja. 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.
dar_baja 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 →