# `fit.ilook/face-analysis` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. 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://anlyon.dev/servers/fit.ilook/face-analysis
- JSON: https://anlyon.dev/api/v1/servers/fit.ilook/face-analysis
- Version: 1.3.1 (active)
- Publisher: fit.ilook (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/harshul1404/ilook
- Metadata from the official MCP Registry, synced 2026-10-21T18:12:55.146Z

Title and description, as the publisher wrote them:

```untrusted-server-text
iLook Face Analysis
Analyze user-submitted face photos with a complete report or 13 focused face-analysis tools.
```

Scanned 2026-10-21T18:38:46.465Z over streamable-http.

**14 tools: 1 change things and 13 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 1 | ask |
| Only reads | read | 13 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data 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. | `mcp__face-analysis__analyze_adult_face_age_cues` `mcp__face-analysis__analyze_canthal_tilt` `mcp__face-analysis__analyze_color_palette` `mcp__face-analysis__analyze_face_shape` `mcp__face-analysis__analyze_facial_symmetry` `mcp__face-analysis__analyze_golden_ratio_face` `mcp__face-analysis__analyze_psl_score` `mcp__face-analysis__analyze_skin_appearance` `mcp__face-analysis__calculate_facial_ratios` `mcp__face-analysis__detect_eye_shape` `mcp__face-analysis__find_hairstyle_direction` `mcp__face-analysis__rate_jawline` `mcp__face-analysis__run_attractiveness_test` `mcp__face-analysis__score_face` |
| 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 `run_attractiveness_test` ([annotation-conflict](https://anlyon.dev/methodology#annotation-conflict))

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

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "run_attractiveness_test" says "run": a word for a change.
```


## Changes things (1)

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

### `run_attractiveness_test`

- The name "run_attractiveness_test" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Returns a photo-specific subjective appearance score and visible basis.
```

## Only reads (13)

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

### `analyze_adult_face_age_cues`

- The name "analyze_adult_face_age_cues" says "analyze": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns broad adult presentation cues, not an exact age prediction.
```

### `analyze_canthal_tilt`

- The name "analyze_canthal_tilt" says "analyze": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns left, right, and average visible eye-corner tilt cues.
```

### `analyze_color_palette`

- The name "analyze_color_palette" says "analyze": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns style-oriented palette, contrast, and lighting cues.
```

### `analyze_face_shape`

- The name "analyze_face_shape" says "analyze": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns face shape, runner-up shape, outline cues, and styling direction.
```

### `analyze_facial_symmetry`

- The name "analyze_facial_symmetry" says "analyze": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns photo-specific left-right symmetry cues across visible features.
```

### `analyze_golden_ratio_face`

- The name "analyze_golden_ratio_face" says "analyze": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns an approximate visible Golden Ratio phi score and proportion cues.
```

### `analyze_psl_score`

- The name "analyze_psl_score" says "analyze": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns a broad PSL-style range from visible geometry without false precision.
```

### `analyze_skin_appearance`

- The name "analyze_skin_appearance" says "analyze": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns appearance-only texture, evenness, shine, and lighting cues.
```

### `calculate_facial_ratios`

- The description's first verb is "return": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns visible face-ratio and spacing cues from one photo.
```

### `detect_eye_shape`

- The description's first verb is "return": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns opening shape, corner orientation, and visible eye framing.
```

### `find_hairstyle_direction`

- The name "find_hairstyle_direction" says "find": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns face-shape-based hairstyle and framing direction.
```

### `rate_jawline`

- The description's first verb is "return": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns visible jawline definition, balance, and lower-face cues.
```

### `score_face`

- The description's first verb is "return": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Returns descriptive face-shape context, five subjective appearance scores, and an approximate Golden Ratio phi score for one authorized adult photo.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `face-analysis`:

```json
{
  "permissions": {
    "allow": [
      "mcp__face-analysis__score_face",
      "mcp__face-analysis__analyze_face_shape",
      "mcp__face-analysis__rate_jawline",
      "mcp__face-analysis__analyze_canthal_tilt",
      "mcp__face-analysis__detect_eye_shape",
      "mcp__face-analysis__analyze_adult_face_age_cues",
      "mcp__face-analysis__analyze_facial_symmetry",
      "mcp__face-analysis__analyze_golden_ratio_face",
      "mcp__face-analysis__analyze_psl_score",
      "mcp__face-analysis__calculate_facial_ratios",
      "mcp__face-analysis__analyze_color_palette",
      "mcp__face-analysis__analyze_skin_appearance",
      "mcp__face-analysis__find_hairstyle_direction"
    ],
    "ask": [
      "mcp__face-analysis__run_attractiveness_test"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__face-analysis__score_face`: untrusted-input
- `mcp__face-analysis__analyze_face_shape`: untrusted-input
- `mcp__face-analysis__rate_jawline`: untrusted-input
- `mcp__face-analysis__analyze_canthal_tilt`: untrusted-input
- `mcp__face-analysis__detect_eye_shape`: untrusted-input
- `mcp__face-analysis__analyze_adult_face_age_cues`: untrusted-input
- `mcp__face-analysis__analyze_facial_symmetry`: untrusted-input
- `mcp__face-analysis__analyze_golden_ratio_face`: untrusted-input
- `mcp__face-analysis__run_attractiveness_test`: untrusted-input
- `mcp__face-analysis__analyze_psl_score`: untrusted-input
- `mcp__face-analysis__calculate_facial_ratios`: untrusted-input
- `mcp__face-analysis__analyze_color_palette`: untrusted-input
- `mcp__face-analysis__analyze_skin_appearance`: untrusted-input
- `mcp__face-analysis__find_hairstyle_direction`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-10-22T14:48:00.625Z, unchanged since 2026-10-22T14:48:00.625Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://anlyon.dev/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 | `1` |
| 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://anlyon.dev/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

https://www.ilook.fit/mcp: tools/list returned 14 tools to an anonymous client, including run_attractiveness_test (write)
```