AI agents call listar_alumnos to retrieve information from Moodle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries course enrollment data with no modification, creation, or deletion of data. It performs a straightforward read operation returning user information already available within the course. No side effects or irreversible actions are possible. Severity is low because user enrollment lists are typically non-sensitive institutional data with limited blast radius if exposed.
From the tool's definition Tool name: listar_alumnos. Description states 'List enrolled users in a course' with filtering and retrieval of user data (id, fullname, email, lastaccess, roles, groups). Uses read-only verbs 'List' and 'Returns'.
Attacks that exploit this kind of access
List enrolled users in a course. Filter by role shortname (default: student). Returns id, fullname, email, lastaccess, roles and groups per user. It is categorised as a Read tool in the Moodle MCP Server, which means it retrieves data without modifying state.
Register the Moodle MCP server in PolicyLayer and add a rule for listar_alumnos: 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.
listar_alumnos 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 listar_alumnos 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 listar_alumnos. 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.
listar_alumnos 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 →