AI agents use publicar_preview 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 publishes content (a FichaClase) in preview mode, which creates or modifies data in Moodle. This is a Write operation as it creates a preview publication state rather than executing arbitrary code or permanently deleting data. The 'hidden preview mode' suggests the change is reversible or limited in scope.
From the tool's definition Tool name 'publicar_preview' and description 'Publish a FichaClase in hidden preview mode' indicate creation/publication of pedagogical content with potential state changes.
Attacks that exploit this kind of access
Publish a FichaClase in hidden preview mode. Returns the same shape as publicar_ficha_clase plus. 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 publicar_preview: 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.
publicar_preview 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 publicar_preview 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 publicar_preview. 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.
publicar_preview 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 →