AI agents use enviar_mensaje_moodle 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.
This tool creates and stores new message records in Moodle, making it a Write operation. It modifies system state by adding messages to user inboxes. Severity is medium because while messages can be sent to many users, they are not destructive (can be deleted), not financial, and do not execute arbitrary code.
From the tool's definition Tool sends private messages to one or more users (max 50 recipients per call) via Moodle's core_message_send_instant_messages API. The description explicitly states 'Send a private Moodle message', which creates new message data in the Moodle system.
Attacks that exploit this kind of access
Send a private Moodle message to one or more user ids. Max 50 recipients per call. Uses core_message_send_instant_messages. 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 enviar_mensaje_moodle: 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.
enviar_mensaje_moodle 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 enviar_mensaje_moodle 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 enviar_mensaje_moodle. 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.
enviar_mensaje_moodle 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 →