# Flow Learning System (mcpb · flow-learning-system-0.1.0.mcpb)

Build motion-graphics lessons with sentence-synced TTS for any subject: one sentence, one scene.

- Trust score: 40/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `flow-learning-system-0.1.0.mcpb`: 40/100 (this document), [markdown](https://verifymcp.io/servers/ghlee0786-flow-learning-system/flow-learning-system.md), [page](https://verifymcp.io/servers/ghlee0786-flow-learning-system/flow-learning-system)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/ghlee0786/flow-learning-system/releases/download/v0.1.0/flow-learning-system-0.1.0.mcpb`
- Transport: `stdio`
- SHA-256: `27fb678e69de22c186989fa3541b6fdedc24dbdcfe3f688bdd3c4d468ade4fe3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 12/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs were checked across the 28 of 28 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - Install-script risk not yet assessed.
  - 1 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 36/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1079 tokens (~77/item across 14 items; 13 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (8% 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.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 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 Flow Learning System MCP server?

Flow Learning System ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 27fb678e69de22c186989fa3541b6fdedc24dbdcfe3f688bdd3c4d468ade4fe3; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/ghlee0786/flow-learning-system/releases/download/v0.1.0/flow-learning-system-0.1.0.mcpb`
- SHA-256: `27fb678e69de22c186989fa3541b6fdedc24dbdcfe3f688bdd3c4d468ade4fe3`

### Verify on macOS / Linux

```bash
echo "27fb678e69de22c186989fa3541b6fdedc24dbdcfe3f688bdd3c4d468ade4fe3  flow-learning-system-0.1.0.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\flow-learning-system-0.1.0.mcpb).Hash -eq "27fb678e69de22c186989fa3541b6fdedc24dbdcfe3f688bdd3c4d468ade4fe3"
```

## 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.

### 2026-11-04 (score 40, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 39, +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.

### 2026-10-30 (score 38, +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.

### 2026-10-28 (score 37, +2)

- [functional improvement] Stability: unverified → 0.13

### 2026-10-24 (score 35)

First indexed and scored.

## MCP tools (13)

### `authoring_guide` (~53 tokens)

레슨 JSON 형식(op, 장면 옵션, 위젯), 모션 규칙, TTS 문장 쓰는 법을 담은 가이드. 레슨을 쓰기 전에 읽으세요.

Output parameters:

- `result` (string)

### `course_init` (~79 tokens)

새 코스 폴더를 만듭니다. code_lang: csharp | python, voice: F1~F5, M1~M5.

Input parameters:

- `code_lang` (string)
- `course_dir` (string, required)
- `subtitle` (string)
- `title` (string, required)
- `voice` (string)

### `course_status` (~41 tokens)

코스의 레슨 목록, 장면 수, 형식 문제 수, 음성 상태를 보여 줍니다.

Input parameters:

- `course_dir` (string, required)

### `lesson_get` (~42 tokens)

레슨 JSON 하나를 그대로 돌려줍니다(고쳐 쓸 때).

Input parameters:

- `course_dir` (string, required)
- `lesson_id` (integer, required)

### `lesson_save` (~79 tokens)

레슨 JSON을 검사하고, 오류가 없으면 lessons/NN.json으로 저장합니다(같은 id면 덮어씀).
lesson = {"id": 1, "group": "...", "title": "...", "sub": "...", "ops": [...]}

Input parameters:

- `course_dir` (string, required)
- `lesson` (object, required)

### `lesson_validate` (~57 tokens)

레슨 형식을 검사합니다(없는 코드 줄, 모르는 op·위젯, 읽기 어려운 단어 등). lesson_id를 비우면 전체.

Input parameters:

- `course_dir` (string, required)
- `lesson_id`

### `speech_preview` (~54 tokens)

장면마다 TTS가 실제로 읽을 문장을 보여 주고, 영어 단어처럼 읽기 어려운 조각을 표시합니다.

Input parameters:

- `course_dir` (string, required)
- `lesson_id` (integer, required)

### `pronunciation_add` (~58 tokens)

영어 단어의 한글 읽기를 코스에 등록합니다. 예: word="Dictionary", reading="딕셔너리".

Input parameters:

- `course_dir` (string, required)
- `reading` (string, required)
- `word` (string, required)

### `code_verify` (~59 tokens)

코드 블록을 실제로 컴파일·실행해 화면 콘솔 출력(out/write)과 같은지 확인합니다. C#은 mono 또는 dotnet, Python은 python.

Input parameters:

- `course_dir` (string, required)
- `lesson_id`

### `audio_synthesize` (~99 tokens)

Supertonic TTS로 레슨 음성(audio/lNN.mp3)과 문장별 시각표(timing.json)를 만듭니다.
바뀌지 않은 레슨은 건너뜁니다. 레슨이 많으면 lesson_id를 하나씩 주어 나눠 실행하세요.

Input parameters:

- `course_dir` (string, required)
- `force` (boolean)
- `lesson_id`
- `voice`

### `render_3d` (~247 tokens)

Blender로 3D 장면을 렌더해 assets/<name>.png 와 핫스폿 좌표를 만듭니다.
script: bpy 파이썬 코드(장면만 만들면 됨). spot("이름", (x, y, z))로 찍은 3D 위치가 이미지의 어디인지 계산되어,
레슨에서 {"img": ["assets/<name>.png", {"spots": ["이름"], "arrows": [{"from": "a", "to": "b"}]}]}로 가리킬 수 있습니다.
도우미: mat(이름, (r,g,b), rough, metal, emit, sss), paint(obj, mat), spot, camera(위치, 대상, lens), sun, area, world, look_at, cylinder_between.
Blender가 PATH에 없으면 FLS_BLENDER 환경 변수에 실행 파일 경로를 넣으세요.

Input parameters:

- `course_dir` (string, required)
- `height` (integer)
- `name` (string, required)
- `samples` (integer)
- `script` (string, required)
- `width` (integer)

### `assets_list` (~43 tokens)

코스의 이미지와 각 이미지의 핫스폿 이름·좌표(0~1)를 보여 줍니다.

Input parameters:

- `course_dir` (string, required)

### `course_build` (~58 tokens)

한 파일짜리 HTML 플레이어(dist/index.html)와 음성 파일을 만듭니다. 음성이 없는 레슨은 소리 없이 예상 시간으로 진행합니다.

Input parameters:

- `course_dir` (string, required)
- `out_dir`

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ghlee0786-flow-learning-system/flow-learning-system#diagnostics

## Score history

- 2026-11-05: 40
- 2026-11-04: 40
- 2026-11-03: 39
- 2026-11-02: 39
- 2026-11-01: 39
- 2026-10-31: 38
- 2026-10-30: 38
- 2026-10-29: 37
- 2026-10-28: 37
- 2026-10-27: 35
- 2026-10-26: 35
- 2026-10-25: 35
- 2026-10-24: 35

## Common questions

### What is the Flow Learning System MCP server?

Flow Learning System is an MCP server listed in the public MCP registry as io.github.ghlee0786/flow-learning-system. Build motion-graphics lessons with sentence-synced TTS for any subject: one sentence, one scene. This page covers its MCPB bundle (https://github.com/ghlee0786/flow-learning-system/releases/download/v0.1.0/flow-learning-system-0.1.0.mcpb).

### Is the Flow Learning System MCP server safe to use?

Flow Learning System scores 40 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 Flow Learning System MCP server expose?

Flow Learning System exposes 13 tools: authoring_guide, course_init, course_status, lesson_get, lesson_save, and 8 more. Their descriptions and schemas cost roughly 969 tokens of context every time the server is loaded.

### What licence is the Flow Learning System MCP server under?

Flow Learning System declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/ghlee0786/flow-learning-system
- Changelog RSS feed: https://verifymcp.io/servers/ghlee0786-flow-learning-system/flow-learning-system.xml
- Changelog JSON feed: https://verifymcp.io/servers/ghlee0786-flow-learning-system/flow-learning-system.json
- HTML version of this page: https://verifymcp.io/servers/ghlee0786-flow-learning-system/flow-learning-system