# validate_gift

Check questions in GIFT before import_questions, without Moodle: each question split at blank lines as Moodle's importer does, with its type in Moodle's names, title, text and answers, and each problem with its line (a question Moodle can't read, a weight it doesn't take, a multiple choice with no right answer, a matching question with fewer than two pairs); ordering questions in their own GIFT ({>…}) too, as Moodle exports them. Fix what it reports and check again; valid means Moodle should import every question.

Agent View of the PolicyLayer registry record for `validate_gift`. HTML page: https://policylayer.com/tools/falkenslab-moodle-mcp/validate-gift

## Facts

- Tool: `validate_gift`
- Server: Moodle (`@falkenslab/moodle-mcp`) — https://policylayer.com/tools/falkenslab-moodle-mcp.md
- Install: `npx -y @falkenslab/moodle-mcp`
- Homepage: https://www.npmjs.com/package/@falkenslab/moodle-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 2
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `file` | string | no | Or an absolute path to a local GIFT file |
| `text` | string | no | The questions in GIFT |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "validate_gift",
    "arguments": {}
  }
}
```

## Why validate_gift is rated Low

Even though validate_gift only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signals: Accepts file system path (file) · Bulk/mass operation — affects multiple targets

## Use case

AI agents call validate_gift to retrieve information from Moodle without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Moodle:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "validate_gift": {}
  }
}
```

## Other tools on Moodle (232)

- `delete_activity` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-activity.md
- `delete_book_chapter` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-book-chapter.md
- `delete_database_entry` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-database-entry.md
- `delete_database_field` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-database-field.md
- `delete_event` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-event.md
- `delete_feedback_item` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-feedback-item.md
- `delete_feedback_template` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-feedback-template.md
- `delete_glossary_entry` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-glossary-entry.md
- `delete_grade_category` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-grade-category.md
- `delete_grade_item` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-grade-item.md
- `delete_group` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-group.md
- `delete_grouping` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-grouping.md
- `delete_lesson_page` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-lesson-page.md
- `delete_post` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-post.md
- `delete_question_category` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-question-category.md
- `delete_questions` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-questions.md
- `delete_section` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-section.md
- `delete_workshop_example` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/delete-workshop-example.md
- `override_workshop_grade` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/override-workshop-grade.md
- `remove_quiz_slot` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/remove-quiz-slot.md
- `remove_site` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/remove-site.md
- `remove_workshop_reviewer` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/remove-workshop-reviewer.md
- `reset_course` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/reset-course.md
- `unenrol_user` — Destructive — https://policylayer.com/tools/falkenslab-moodle-mcp/unenrol-user.md
- `browser_navigate` — Execute — https://policylayer.com/tools/falkenslab-moodle-mcp/browser-navigate.md
- `browser_wait` — Execute — https://policylayer.com/tools/falkenslab-moodle-mcp/browser-wait.md
- `enrol_users` — Execute — https://policylayer.com/tools/falkenslab-moodle-mcp/enrol-users.md
- `grade_forum_user` — Execute — https://policylayer.com/tools/falkenslab-moodle-mcp/grade-forum-user.md
- `rate` — Execute — https://policylayer.com/tools/falkenslab-moodle-mcp/rate.md
- `start_quiz_attempt` — Execute — https://policylayer.com/tools/falkenslab-moodle-mcp/start-quiz-attempt.md
- …and 202 more: https://policylayer.com/tools/falkenslab-moodle-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=falkenslab-moodle-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/falkenslab-moodle-mcp