# `app.apick/vision` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/app.apick/vision
- JSON: https://radar.anlyon.com/api/v1/servers/app.apick/vision
- Version: 1.3.0 (active)
- Publisher: app.apick (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/lead788/apick-mcp
- Metadata from the official MCP Registry, synced 2026-11-17T10:17:38.304Z

Title and description, as the publisher wrote them:

```untrusted-server-text
APICK Vision
Image/video analysis: NSFW detection, object detection, thumbnails
```

Scanned 2026-11-17T10:17:46.111Z over streamable-http.

**7 tools: 5 change things and 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 5 | ask |
| Only reads | read | 2 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

- **warn** Annotations that disagree with the tool in `word_cloud` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "word_cloud" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"openWorldHint":false}; The description's first verb is "generate": a word for a change.
```


## Changes things (5)

Creates or changes something that can be changed back. Claude Code: ask.

### `extract_video_thumbnail`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Extract preview thumbnail images from a video at regular intervals and return them as a ZIP file. 동영상에서 일정 구간마다 미리보기 이미지를 추출해 ZIP 파일로 반환합니다. [호출당 10포인트]
```

### `face_detection`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Detect faces in an image and return their coordinates. 이미지 파일에서 얼굴을 인식해 해당 좌표를 반환합니다. use_feature=1 입력 시 얼굴 특징 정보를 함께 반환합니다. [호출당 3포인트]
```

### `nsfw_detection`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Detect whether an image contains NSFW (violent or sexually explicit) content and return an nsfw_score. 이미지가 NSFW(폭력적·선정적) 콘텐츠인지 탐지해 nsfw_score 를 반환합니다. detail=1 입력 시 세부 판정 결과를 함께 반환합니다. [호출당 10포인트]
```

### `video_to_mp3`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

Description, as the server wrote it:

```untrusted-server-text
Extract the audio track of a video file as an MP3 file. 동영상 파일에서 오디오를 추출해 MP3 파일로 반환합니다. [호출당 30포인트]
```

### `word_cloud`

- The description's first verb is "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Generate a word cloud image (JPEG) from input text, sizing each word by frequency. 입력 텍스트를 구성하는 단어의 중요도(빈도수)에 따라 서로 다른 크기의 단어로 이루어진 워드클라우드 이미지(JPEG)를 생성해 반환합니다. [호출당 10포인트]
```

## Only reads (2)

Looks things up and changes nothing. Claude Code: allow.

### `face_similarity`

- The description's first verb is "compare": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Compare the main face in a reference image with the face in another image and return a 0-1 similarity score, a match decision and a level (high/medium/low). Use it to check an ID card photo against a selfie. 기준 사진과 비교 사진의 대표 얼굴이 같은 사람인지 0~1 점수와 판정(is_match)으로 알려줍니다. 신분증 사진과 셀피 대조에 씁니다. [호출당 10포인트]
```

### `image_similarity`

- The description's first verb is "compare": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Compare a base image with another image and return a similarity score. 기준 이미지와 비교 대상 이미지의 유사도를 분석해 점수를 반환합니다. 원본 검증, 중복 이미지 탐지 등에 사용합니다. [호출당 10포인트]
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `vision`:

```json
{
  "permissions": {
    "allow": [
      "mcp__vision__image_similarity",
      "mcp__vision__face_similarity"
    ],
    "ask": [
      "mcp__vision__nsfw_detection",
      "mcp__vision__video_to_mp3",
      "mcp__vision__extract_video_thumbnail",
      "mcp__vision__word_cloud",
      "mcp__vision__face_detection"
    ],
    "deny": []
  }
}
```

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:25:59.592Z, unchanged since 2026-11-20T19:25:59.592Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `6` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.

https://apick.app/mcp/vision: tools/list returned 8 tools to an anonymous client, including nsfw_detection (write), video_to_mp3 (write), extract_video_thumbnail (write), word_cloud (write), face_detection (write) and 1 more
```

Posture changes:

- 2026-11-20T19:25:59.592Z: Tools that change things, listed without credentials `5` -> `6`
