Edit an existing question (typo fix, reformulation, feedback tweak). Writes directly to DB, bypass Moodle 5.0.2 qbank form bug. Input: course_id, question_id, optional name / question_text / answers[]. Coverage: name, text, answers (answer/feedback/fraction).
AI agents use modificar_pregunta 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 modifies educational content (quiz questions) in a Moodle database. While reversible (not deletion), it can alter pedagogical material at scale. The direct database write bypassing form validation increases risk of unintended modifications.
From the tool's definition Tool description states 'Edit an existing question' and 'Writes directly to DB' with coverage of 'name, text, answers'. These are modification operations that create or alter data reversibly.
Attacks that exploit this kind of access
Edit an existing question (typo fix, reformulation, feedback tweak). Writes directly to DB, bypass Moodle 5.0.2 qbank form bug. Input: course_id, question_id, optional name / question_text / answers[]. Coverage: name, text, answers (answer/feedback/fraction). 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 modificar_pregunta: 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.
modificar_pregunta 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 modificar_pregunta 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 modificar_pregunta. 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.
modificar_pregunta 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 →