# PLATO MCP (remote · plato-mcp.onrender.com)

PLATO (Pusan National University LMS) MCP server via Moodle Web Service API + ubboard scraping

- Trust score: 69/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `plato-mcp.onrender.com`: 69/100 (this document), [markdown](https://verifymcp.io/servers/jin-1119-plato-mcp/plato-mcp.md), [page](https://verifymcp.io/servers/jin-1119-plato-mcp/plato-mcp)

## Channel facts

- Endpoint: `https://plato-mcp.onrender.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (submit_assignment).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 5739 tokens (~85/item across 67 items; 67 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 67 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the PLATO MCP server?

PLATO MCP is a hosted endpoint at https://plato-mcp.onrender.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http jin-1119-plato-mcp 'https://plato-mcp.onrender.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "jin-1119-plato-mcp": {
      "url": "https://plato-mcp.onrender.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jin-1119-plato-mcp": {
      "type": "http",
      "url": "https://plato-mcp.onrender.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.jin-1119-plato-mcp]
url = "https://plato-mcp.onrender.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jin-1119-plato-mcp": {
      "type": "remote",
      "url": "https://plato-mcp.onrender.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jin-1119-plato-mcp --url 'https://plato-mcp.onrender.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  jin-1119-plato-mcp:
    url: "https://plato-mcp.onrender.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "jin-1119-plato-mcp": {
      "Transport": "http",
      "Url": "https://plato-mcp.onrender.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add jin-1119-plato-mcp -t streamable-http -u 'https://plato-mcp.onrender.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "jin-1119-plato-mcp": {
      "type": "http",
      "url": "https://plato-mcp.onrender.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 65, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-28 (score 65)

First indexed and scored.

## MCP tools (67)

### `list_courses` (~21 tokens)

List the courses the logged-in PLATO account is enrolled in.

Output parameters:

- `result` (array)

### `get_course_contents` (~44 tokens)

Get a course's weekly sections, modules, and file links.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `result` (array)

### `list_assignments` (~38 tokens)

List assignments across one or more courses, with due dates.

Input parameters:

- `course_ids` (array, required): One or more course ids to list assignments for.

Output parameters:

- `result` (array)

### `get_assignment_detail` (~61 tokens)

Get one assignment's details and this account's submission status.

Input parameters:

- `assignment_id` (integer, required): Assignment id, e.g. from list_assignments.
- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `assignment`
- `extra`
- `feedback`
- `previousattempts` (array)
- `submission`

### `submit_assignment` (~484 tokens)

Submit text and/or file attachments for an assignment. IRREVERSIBLE once dry_run=False.

        Call with dry_run=True (default) first, show the preview to the user, and
        only call again with dry_run=False (same parameters) after they explicitly
        confirm. Provide text, file_paths/file_contents, or both -- whichever this
        assignment actually accepts (see get_assignment_detail).

        file_paths works only when this server is running locally (stdio, e.g.
        Claude Code/Desktop) -- rejected with a clear error over a remote
        (streamable-http, e.g. a Claude.ai Connector) connection, mirroring
        download_course_file's own stdio-vs-remote split. file_contents works
        over either transport and is the only option remotely, since this
        server's disk is not reachable by you there.

Input parameters:

- `assignment_id` (integer, required): Assignment id, e.g. from list_assignments.
- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.
- `dry_run` (boolean): If True (default), only preview the submission without sending it. Call again with dry_run=False (same parameters) to actually submit it.
- `file_contents`: File attachments as {filename, content_base64} -- works over either transport, and is the only way to attach files when this server is running remotely (streamable-http), since it has no local filesy…
- `file_paths`: Local filesystem paths to upload as file attachments. Only works when this server is running locally (stdio) -- rejected with a clear error over a remote/streamable-http connection (use file_contents…
- `text` (string): Plain-text submission content. Omit (empty string) for a file-only submission. Rejected if this assignment doesn't accept online text -- check get_assignment_detail's onlinetext_submission.enabled fi…

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `remove_submission` (~238 tokens)

Withdraw/clear this account's own submission for an assignment.
        IRREVERSIBLE and DESTRUCTIVE once dry_run=False -- this discards
        already-submitted work (files/text), not a draft.

        KNOWN ISSUE: live testing found dry_run=False currently fails with
        an "invalid parameter" error from PLATO every time (the real
        required parameter shape wasn't determined -- see
        remove_submission_for's docstring). dry_run=True (preview) works
        and is safe to call. Do not rely on dry_run=False actually working
        until this is fixed.

        Call with dry_run=True (default) first, show the preview to the user,
        and only call again with dry_run=False after they explicitly confirm.

Input parameters:

- `assignment_id` (integer, required): Assignment id, e.g. from list_assignments.
- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.
- `dry_run` (boolean): If True (default), only preview the removal without doing it. Call again with dry_run=False (same parameters) to actually remove it.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `get_grades` (~44 tokens)

Get this account's grade items for a course, if visible.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `available` (boolean)
- `courseid` (integer)
- `gradeitems` (array)
- `message`

### `get_grades_access_info` (~84 tokens)

Check what grade-related permissions this account has in a
        course -- e.g. whether it can see its own grades vs. (as a
        teacher/TA) everyone's grades. Most student accounts will see
        canviewallgrades=False.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `canviewallgrades` (boolean): True for teachers/TAs who can see everyone's grades.
- `canviewmygrades` (boolean)
- `canviewusergradereport` (boolean)

### `list_calendar_events` (~42 tokens)

List upcoming calendar events within the next `days_ahead` days.

Input parameters:

- `days_ahead` (integer): How many days ahead of now to include events for.

Output parameters:

- `result` (array)

### `get_calendar_access_info` (~39 tokens)

Check this account's calendar-management permissions -- a
        student account can typically manage its own personal entries
        only, not course/group entries.

Output parameters:

- `canmanageentries` (boolean)
- `canmanagegroupentries` (boolean)
- `canmanageownentries` (boolean)

### `create_calendar_event` (~171 tokens)

Create a personal calendar entry. IRREVERSIBLE once dry_run=False.
        Only personal ("user") events are supported -- course/group events
        are not something a student account can create.

        Call with dry_run=True (default) first, show the preview to the user,
        and only call again with dry_run=False after they explicitly confirm.

Input parameters:

- `description` (string): Optional event description.
- `dry_run` (boolean): If True (default), only preview the event without creating it. Call again with dry_run=False (same parameters) to actually create it.
- `duration_seconds` (integer): Event duration in seconds, 0 for a point-in-time event.
- `name` (string, required): Event title.
- `timestart` (integer, required): Unix timestamp for the event's start.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `delete_calendar_event` (~110 tokens)

Delete a personal calendar entry this account owns. IRREVERSIBLE
        once dry_run=False.

        Call with dry_run=True (default) first, show the preview to the user,
        and only call again with dry_run=False after they explicitly confirm.

Input parameters:

- `dry_run` (boolean): If True (default), only preview the deletion without doing it. Call again with dry_run=False (same parameters) to actually delete it.
- `event_id` (integer, required): Calendar event id to delete.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `get_unread_messages` (~33 tokens)

Get this account's unread PLATO notifications.

Input parameters:

- `limit` (integer): Maximum number of unread notifications to return.

Output parameters:

- `result` (array)

### `get_unread_notification_count` (~64 tokens)

Get a count of this account's unread notifications (a cheaper
        check than get_unread_messages when you don't need the content).
        Note: PLATO has person-to-person messaging disabled site-wide, so
        this counts notifications only, not conversation messages.

Output parameters:

- `result` (integer)

### `list_notices` (~41 tokens)

List announcements posted to a course's Notices board.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `result` (array)

### `get_notice_detail` (~60 tokens)

Get the full text of one notice/announcement.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.
- `post_id` (integer, required): Notice post id, e.g. from list_notices.

Output parameters:

- `board_id` (integer)
- `content_html` (string)
- `post_id` (integer)
- `posted_at`
- `title` (string)
- `view_count`
- `writer`: Display name of who posted this. For Notices this is course staff (instructor/TA); for Q&A it can be any classmate. Passed through as-is -- see docs/pii_review.md for why, and its caveats.

### `list_qna` (~42 tokens)

List questions posted to a course's Q&A board.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `result` (array)

### `get_qna_detail` (~70 tokens)

Get one Q&A question's text. Does not include replies -- see issue #23.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.
- `post_id` (integer, required): Q&A post id, e.g. from list_qna.

Output parameters:

- `board_id` (integer)
- `content_html` (string)
- `post_id` (integer)
- `posted_at`
- `title` (string)
- `view_count`
- `writer`: Display name of who posted this. For Notices this is course staff (instructor/TA); for Q&A it can be any classmate. Passed through as-is -- see docs/pii_review.md for why, and its caveats.

### `post_qna_question` (~164 tokens)

Post a new question to a course's Q&A board. IRREVERSIBLE and VISIBLE
        to the instructor once dry_run=False (posted as private/secret by default).

        Call with dry_run=True (default) first, show the preview to the user, and
        only call again with dry_run=False after they explicitly confirm.

Input parameters:

- `content_text` (string, required): Body text of the Q&A question.
- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.
- `dry_run` (boolean): If True (default), only preview without posting. Call again with dry_run=False (same parameters) to actually post it.
- `subject` (string, required): Subject/title of the Q&A question.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `download_course_file` (~270 tokens)

Download a course file (the `fileurl` from get_course_contents).

        Running locally (stdio, e.g. Claude Code/Desktop): saves the file to
        `save_path` on this machine and returns the saved path -- `save_path`
        is required in this case.

        Running as a remote/hosted server (streamable-http, e.g. reached via
        a Claude.ai web/mobile Connector): this server's own disk is not
        reachable by you, so do NOT pass `save_path` -- it will be rejected.
        Instead the file is fetched here and returned inline as base64
        content for you to decode and present, unless it's too large, in
        which case a direct authenticated download URL is returned instead
        (that URL embeds a live PLATO access token: do not share it or a
        chat transcript containing it).

        Only common course-material extensions are allowed (pdf, office
        docs, images, zip, txt); local downloads over the configured size
        limit are rejected.

Input parameters:

- `file_url` (string, required): The `fileurl` value from get_course_contents.
- `save_path`: Local filesystem path to save to. Required when running locally (stdio); must be omitted when running remotely over HTTP.

Output parameters:

- `result`

### `get_course_completion_status` (~102 tokens)

Get this account's overall course-completion status, if the course
        has course-level completion criteria configured. Most courses on
        this platform don't (available=False, with a message explaining
        why) -- try get_activity_completion_status for per-activity
        progress instead, or get_course_contents's per-module `completed`
        flag.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `available` (boolean)
- `completed`
- `courseid` (integer)
- `criteria` (array)
- `message`

### `get_activity_completion_status` (~125 tokens)

Get this account's completion status for every activity/module in
        a course -- richer than get_course_contents's per-module `completed`
        flag (includes tracking rules, e.g. 'must view' vs 'must spend N
        minutes'). For `vod` (video lecture) modules specifically, prefer
        get_course_contents, whose per-module `vod_progress` field also
        includes watch-percentage and deadline info this function doesn't
        return.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `result` (array)

### `get_upcoming_action_events` (~101 tokens)

Get Moodle's own "what needs action soon" feed -- assignments due,
        video lectures with a watch deadline, etc. -- sorted by urgency, from
        now onward. Unlike combining list_assignments + get_calendar_events,
        this is Moodle's own cross-activity prioritized view and may surface
        activity types (e.g. vod watch deadlines) those tools don't.

Input parameters:

- `limit` (integer): Maximum number of upcoming events to return.

Output parameters:

- `result` (array)

### `get_courses_by_timeline` (~96 tokens)

List enrolled courses filtered by Moodle's own timeline
        classification (in-progress/future/past), based on course start/end
        dates. Unlike list_courses (which returns everything unfiltered),
        this answers "what am I actually taking right now" directly.

Input parameters:

- `classification` (string): 'inprogress' (currently running, the default), 'future' (not started yet), or 'past' (ended).

Output parameters:

- `result` (array)

### `get_grades_overview` (~66 tokens)

Get this account's overall grade for every enrolled course in one
        call. For the individual grade *items* within one course (e.g. each
        assignment's score), use get_grades instead -- this tool only
        returns one summary grade per course.

Output parameters:

- `result` (array)

### `list_quizzes` (~34 tokens)

List quizzes across one or more courses.

Input parameters:

- `course_ids` (array, required): One or more course ids to list quizzes for.

Output parameters:

- `result` (array)

### `get_quiz_attempts` (~39 tokens)

Get this account's past attempts at one quiz.

Input parameters:

- `quiz_id` (integer, required): Quiz id, e.g. from list_quizzes.

Output parameters:

- `result` (array)

### `get_quiz_best_grade` (~48 tokens)

Get this account's best grade on one quiz, if any attempt has
        been graded.

Input parameters:

- `quiz_id` (integer, required): Quiz id, e.g. from list_quizzes.

Output parameters:

- `grade`
- `gradetopass`
- `hasgrade` (boolean)

### `get_quiz_access_information` (~84 tokens)

Check whether this account can currently attempt a quiz, and
        why not if blocked (e.g. time window, password, previous
        attempts exhausted). UNVERIFIED against a real quiz -- call this
        before start_quiz_attempt and sanity-check the result.

Input parameters:

- `quiz_id` (integer, required): Quiz id, e.g. from list_quizzes.

Output parameters:

- `accessrules` (array)
- `canattempt` (boolean)
- `canmanage` (boolean)
- `canpreview` (boolean)
- `canreviewmyattempts` (boolean)
- `canviewreports` (boolean)
- `preventaccessreasons` (array): Human-readable reasons attempting is currently blocked, if any.

### `get_quiz_required_qtypes` (~72 tokens)

List the question types used in a quiz (e.g. 'multichoice',
        'truefalse', 'essay') -- useful to know what kind of answers
        to expect before starting an attempt.

Input parameters:

- `quiz_id` (integer, required): Quiz id, e.g. from list_quizzes.

Output parameters:

- `result` (array)

### `get_quiz_feedback_for_grade` (~79 tokens)

Get the grade-boundary feedback text configured for a quiz at
        a given grade (e.g. 'You passed!' / 'Please review chapter 3').

Input parameters:

- `grade` (number, required): A grade value to look up feedback text for.
- `quiz_id` (integer, required): Quiz id, e.g. from list_quizzes.

Output parameters:

- `feedbacktext`
- `feedbacktextformat`

### `get_quiz_combined_review_options` (~73 tokens)

Check which review details (marks, feedback, right answers) this
        account is allowed to see for a quiz's attempts.

Input parameters:

- `attempt_id`: Optional: a specific attempt id to check options for.
- `quiz_id` (integer, required): Quiz id, e.g. from list_quizzes.

Output parameters:

- `feedback` (boolean)
- `generalfeedback` (boolean)
- `marks` (boolean)
- `overallfeedback` (boolean)
- `rightanswer` (boolean)

### `start_quiz_attempt` (~153 tokens)

Start a new attempt at a quiz. IRREVERSIBLE once dry_run=False --
        consumes one of the quiz's limited attempts. UNVERIFIED against a
        real quiz -- call get_quiz_access_information first and check
        canattempt/preventaccessreasons.

        Call with dry_run=True (default) first, show the preview to the
        user, and only call again with dry_run=False after they explicitly
        confirm.

Input parameters:

- `dry_run` (boolean): If True (default), only preview starting the attempt. Call again with dry_run=False (same parameters) to actually start it.
- `quiz_id` (integer, required): Quiz id, e.g. from list_quizzes.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `get_quiz_attempt_data` (~107 tokens)

Get the questions for one page of an in-progress quiz attempt.
        Each question's `html` is Moodle's own rendered question form --
        parse it for the actual answer-field names before calling
        save_quiz_attempt_responses/process_quiz_attempt. UNVERIFIED
        against a real quiz.

Input parameters:

- `attempt_id` (integer, required): Attempt id, e.g. from start_quiz_attempt.
- `page` (integer): Quiz page number, 0-indexed.

Output parameters:

- `nextpage`
- `questions` (array)

### `get_quiz_attempt_summary` (~57 tokens)

Get a summary of all questions in an attempt (answered/
        unanswered), across all pages. UNVERIFIED against a real quiz.

Input parameters:

- `attempt_id` (integer, required): Attempt id, e.g. from start_quiz_attempt.

Output parameters:

- `questions` (array)
- `totalunanswered`

### `get_quiz_attempt_review` (~74 tokens)

Get the grade and per-question review for a finished quiz
        attempt. UNVERIFIED against a real quiz.

Input parameters:

- `attempt_id` (integer, required): Attempt id, e.g. from start_quiz_attempt.
- `page` (integer): Page number, 0-indexed, or -1 for all pages.

Output parameters:

- `grade`
- `questions` (array)

### `save_quiz_attempt_responses` (~166 tokens)

Save in-progress answers WITHOUT finishing the attempt -- can
        still be changed later. UNVERIFIED against a real quiz.

        Call with dry_run=True (default) first, show the preview to the
        user, and only call again with dry_run=False after they explicitly
        confirm.

Input parameters:

- `attempt_id` (integer, required): Attempt id, e.g. from start_quiz_attempt.
- `dry_run` (boolean): If True (default), only preview saving without doing it. Call again with dry_run=False (same parameters) to actually save it.
- `page` (integer): Quiz page number these responses are for.
- `responses` (object, required): Moodle question-form field name -> answer value, parsed from get_quiz_attempt_data's returned HTML.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `process_quiz_attempt` (~210 tokens)

Submit answers for a quiz attempt. IRREVERSIBLE once
        dry_run=False AND finish_attempt=True -- that is the final,
        graded submission and cannot be undone. UNVERIFIED against a
        real quiz.

        Call with dry_run=True (default) first, show the preview to the
        user -- especially before finish_attempt=True -- and only call
        again with dry_run=False after they explicitly confirm.

Input parameters:

- `attempt_id` (integer, required): Attempt id, e.g. from start_quiz_attempt.
- `dry_run` (boolean): If True (default), only preview without doing it. Call again with dry_run=False (same parameters) to actually submit it.
- `finish_attempt` (boolean): If True, this is the FINAL submission -- the attempt is locked and graded. If False, this just records answers for the current page.
- `responses` (object, required): Moodle question-form field name -> answer value, parsed from get_quiz_attempt_data's returned HTML.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `list_forums` (~80 tokens)

List standard Moodle forums across one or more courses. NOT the
        same as PLATO's notice/Q&A board (use list_notices/list_qna for
        that) -- this covers the separate, less-commonly-used mod_forum
        module.

Input parameters:

- `course_ids` (array, required): One or more course ids to list forums for.

Output parameters:

- `result` (array)

### `get_forum_discussions` (~38 tokens)

List discussion threads in one standard Moodle forum.

Input parameters:

- `forum_id` (integer, required): Forum id, e.g. from list_forums.

Output parameters:

- `result` (array)

### `get_discussion_posts` (~39 tokens)

Get all posts in one forum discussion thread.

Input parameters:

- `discussion_id` (integer, required): Discussion id, e.g. from get_forum_discussions.

Output parameters:

- `result` (array)

### `add_discussion` (~133 tokens)

Start a new discussion thread in a forum. IRREVERSIBLE once dry_run=False.

        Call with dry_run=True (default) first, show the preview to the user,
        and only call again with dry_run=False after they explicitly confirm.

Input parameters:

- `dry_run` (boolean): If True (default), only preview the new discussion without posting it. Call again with dry_run=False (same parameters) to actually post.
- `forum_id` (integer, required): Forum id, e.g. from list_forums.
- `message` (string, required): Thread body content.
- `subject` (string, required): Thread subject/title.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `add_discussion_post` (~134 tokens)

Reply to a forum discussion thread. IRREVERSIBLE once dry_run=False.

        Call with dry_run=True (default) first, show the preview to the user,
        and only call again with dry_run=False after they explicitly confirm.

Input parameters:

- `discussion_id` (integer, required): Discussion id, e.g. from get_forum_discussions.
- `dry_run` (boolean): If True (default), only preview the reply without sending it. Call again with dry_run=False (same parameters) to actually post it.
- `message` (string, required): Reply content.
- `subject`: Optional subject override for the reply.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `get_course_updates_since` (~139 tokens)

Get what changed in a course since a given time -- configuration,
        completion, grades, submissions, etc. Only reports modules that
        implement Moodle's change-tracking (confirmed: the standard `assign`
        module does; this platform's own custom lecture-file/board/video
        modules do not, so this won't catch a new ubfile lecture or ubboard
        post -- use get_course_contents/list_notices to check those instead.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.
- `since` (integer, required): Unix timestamp -- report changes after this point in time.

Output parameters:

- `result` (array)

### `get_course_module` (~45 tokens)

Resolve a single course module by its id directly, without
        fetching and filtering the whole course's contents.

Input parameters:

- `cmid` (integer, required): Course module id (cmid).

Output parameters:

- `course` (integer)
- `id` (integer): Course module id (cmid).
- `instance` (integer)
- `modname` (string)
- `name` (string)
- `section`
- `sectionnum`

### `search_courses` (~50 tokens)

Search PLATO's entire course catalog by name -- not limited to
        this account's enrolled courses (use list_courses for that).

Input parameters:

- `search_text` (string, required): Text to search for in course names.

Output parameters:

- `result` (array)

### `get_recent_courses` (~22 tokens)

Get this account's recently-accessed courses, most recent first.

Output parameters:

- `result` (array)

### `get_recent_items` (~34 tokens)

Get this account's recently-accessed course modules (files,
        assignments, etc.) across all courses, most recent first.

Output parameters:

- `result` (array)

### `get_starred_courses` (~23 tokens)

Get this account's starred/favourited courses, if any.

Output parameters:

- `result` (array)

### `list_video_conferences` (~83 tokens)

List BigBlueButton video-conference activities across one or
        more courses. Joining a meeting is not supported by this server --
        this tool is read-only coverage only. Zoom activities (mod_zoom)
        are not covered -- no real instance has existed to verify against.

Input parameters:

- `course_ids` (array, required): One or more course ids to list video conferences for.

Output parameters:

- `result` (array)

### `list_lessons` (~62 tokens)

List Lesson activities across one or more courses. Taking a
        lesson (answering pages) is not supported by this server -- this
        tool is read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list lessons for.

Output parameters:

- `result` (array)

### `list_workshops` (~63 tokens)

List Workshop (peer assessment) activities across one or more
        courses. Submitting or assessing work is not supported by this
        server -- this tool is read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list workshops for.

Output parameters:

- `result` (array)

### `list_feedbacks` (~62 tokens)

List Feedback (survey) activities across one or more courses.
        Responding to a survey is not supported by this server -- this
        tool is read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list feedback activities for.

Output parameters:

- `result` (array)

### `list_choices` (~60 tokens)

List Choice (single-question poll) activities across one or
        more courses. Voting is not supported by this server -- this
        tool is read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list choice activities for.

Output parameters:

- `result` (array)

### `list_surveys` (~57 tokens)

List Survey activities across one or more courses. Answering is
        not supported by this server -- this tool is read-only coverage
        only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list survey activities for.

Output parameters:

- `result` (array)

### `list_scorms` (~68 tokens)

List SCORM packaged-content activities across one or more
        courses. Launching/tracking a SCORM attempt is not supported by
        this server -- this tool is read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list SCORM packages for.

Output parameters:

- `result` (array)

### `list_h5p_activities` (~66 tokens)

List H5P interactive-content activities across one or more
        courses. Attempt results are not supported by this server -- this
        tool is read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list H5P activities for.

Output parameters:

- `result` (array)

### `list_glossaries` (~60 tokens)

List Glossary activities across one or more courses. Reading/
        adding entries is not supported by this server -- this tool is
        read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list glossaries for.

Output parameters:

- `result` (array)

### `list_database_activities` (~63 tokens)

List Database ("mod_data") activities across one or more
        courses. Reading/adding entries is not supported by this server --
        this tool is read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list database activities for.

Output parameters:

- `result` (array)

### `list_wikis` (~58 tokens)

List Wiki activities across one or more courses. Reading/
        editing pages is not supported by this server -- this tool is
        read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list wikis for.

Output parameters:

- `result` (array)

### `list_chats` (~66 tokens)

List Chat (real-time chat room) activities across one or more
        courses. Reading/sending chat messages is not supported by this
        server -- this tool is read-only coverage only.

Input parameters:

- `course_ids` (array, required): One or more course ids to list chat rooms for.

Output parameters:

- `result` (array)

### `get_user_profile` (~73 tokens)

Get a user's profile, scoped to a shared course (not a global
        user search -- see docs/pii_review.md).

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id both accounts share.
- `userid`: User id to look up. Omit to get this account's own profile.

Output parameters:

- `department`
- `email`: Only populated for the caller's own profile or where the course context grants visibility -- see docs/pii_review.md.
- `fullname` (string)
- `id` (integer)
- `institution`
- `preferences` (array)
- `profileimageurl`
- `username`

### `get_private_files_info` (~33 tokens)

Get a summary (file/folder count, total size) of this account's
        Moodle private files area.

Output parameters:

- `filecount` (integer)
- `filesize` (integer)
- `foldercount` (integer)

### `get_user_preferences` (~47 tokens)

Get this account's Moodle user preferences. Note: most of these
        are internal UI state (e.g. which dashboard sections are
        collapsed), not information meaningful on its own.

Output parameters:

- `result` (array)

### `add_private_file` (~159 tokens)

Upload a file to this account's Moodle private files area.
        IRREVERSIBLE once dry_run=False -- no delete tool exists for
        private files yet, so this permanently adds the file until the
        user removes it via PLATO's own UI. Only works when this server
        is running locally (stdio).

        Call with dry_run=True (default) first, show the preview to the
        user, and only call again with dry_run=False after they explicitly
        confirm.

Input parameters:

- `dry_run` (boolean): If True (default), only preview the upload without doing it. Call again with dry_run=False (same parameters) to actually upload it.
- `file_path` (string, required): Local file path to upload.

Output parameters:

- `dry_run` (boolean)
- `executed` (boolean)
- `message` (string)
- `preview` (object)

### `get_my_course_groups` (~46 tokens)

Get the groups this account belongs to within a course, if any.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `result` (array)

### `get_enrolled_users` (~70 tokens)

Get the list of users enrolled in a course (classmates and
        instructors), with their role. Same data visible in PLATO's own
        participant list to any enrolled student.

Input parameters:

- `course_id` (integer, required): PLATO/Moodle numeric course id, e.g. from list_courses.

Output parameters:

- `result` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/jin-1119-plato-mcp/plato-mcp#diagnostics

## Score history

- 2026-11-05: 69
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 67
- 2026-11-01: 67
- 2026-10-31: 66
- 2026-10-30: 66
- 2026-10-29: 65
- 2026-10-28: 65

## Common questions

### What is the PLATO MCP server?

PLATO MCP is listed in the public MCP registry as io.github.jin-1119/plato-mcp. PLATO (Pusan National University LMS) MCP server via Moodle Web Service API + ubboard scraping. This page covers its hosted endpoint (https://plato-mcp.onrender.com/mcp).

### Is the PLATO MCP server safe to use?

PLATO MCP scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the PLATO MCP server expose?

PLATO MCP exposes 67 tools: list_courses, get_course_contents, list_assignments, get_assignment_detail, submit_assignment, and 62 more. Their descriptions and schemas cost roughly 5,739 tokens of context every time the server is loaded.

### Does the PLATO MCP server require authentication?

No. We connected to PLATO MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the PLATO MCP server still maintained?

PLATO MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://plato-mcp.onrender.com/mcp
- Authorisation metadata: https://plato-mcp.onrender.com/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/jin-1119/plato-mcp
- Changelog RSS feed: https://verifymcp.io/servers/jin-1119-plato-mcp/plato-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/jin-1119-plato-mcp/plato-mcp.json
- HTML version of this page: https://verifymcp.io/servers/jin-1119-plato-mcp/plato-mcp