calificar_manualmente · Moodle MCP: Risk & Policy

WHAT IT DOES

What calificar_manualmente does on Moodle

AI agents use calificar_manualmente 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.

WHY IT NEEDS A POLICY

Why calificar_manualmente needs a policy

Grading is a write operation that modifies student records (grades and feedback) in the learning management system. While grades can theoretically be updated or corrected later (making it reversible rather than destructive), unauthorized or incorrect grading constitutes a significant data modification with pedagogical consequences.

From the tool's definition Tool description states 'Manually grade an assignment submission' and 'save_grade', which modifies student grades and potentially workflow state. The mention of 'marking workflow state' indicates state transitions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

calificar_manualmente Rate-limited

calificar_manualmente stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "calificar_manualmente": {
      "limits": [
        {
          "counter": "calificar_manualmente_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Moodle, so you can run agents against it safely.

FAQ

Questions about calificar_manualmente

What does the calificar_manualmente tool do? +

Manually grade an assignment submission (mod_assign_save_grade). Feedback text is HTML-safe. Supports team grading and marking workflow state. 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.

How do I enforce a policy on calificar_manualmente? +

Register the Moodle MCP server in PolicyLayer and add a rule for calificar_manualmente: 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.

What risk level is calificar_manualmente? +

calificar_manualmente is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit calificar_manualmente? +

Yes. Add a rate_limit block to the calificar_manualmente 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.

How do I block calificar_manualmente completely? +

Set action: deny in the PolicyLayer policy for calificar_manualmente. 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.

What MCP server provides calificar_manualmente? +

calificar_manualmente 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.