enviar_mensaje
⚠️ ESCRITURA. Envia un mensaje a una conversacion (chat interno).
This record as markdown: /tools/moodle-ai-assistant/enviar-mensaje.md
What enviar_mensaje does on Moodle Ai Assistant
AI agents call enviar_mensaje as a supporting operation in Moodle Ai Assistant workflows.
Why enviar_mensaje is rated Low
Without any rule in front of it, every call an agent makes to enviar_mensaje happens silently: no trail, no cap, no way to know it misbehaved until something breaks downstream.
Attacks that exploit this kind of access
The rule that runs enviar_mensaje safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Moodle Ai Assistant, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For enviar_mensaje, this is the rule to start with:
enviar_mensaje gets a rate cap, and everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Moodle Ai Assistant, apply this rule, and every enviar_mensaje call is checked against it from then on.
Questions about enviar_mensaje
⚠️ ESCRITURA. Envia un mensaje a una conversacion (chat interno). It is categorised as a Other tool in the Moodle Ai Assistant MCP Server, which means it performs auxiliary operations.
Register the Moodle Ai Assistant MCP server in PolicyLayer and add a rule for enviar_mensaje: 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 Ai Assistant. Nothing to install.
enviar_mensaje is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the enviar_mensaje 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. 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 is provided by the Moodle Ai Assistant MCP server (rafenixcore/moodle-ai-assistant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Moodle Ai Assistant, and thousands of servers like it.
This server
Across the catalogue