# iLook Face Analysis MCP server

> Analyze authorized adult face photos for face shape, symmetry, Golden Ratio, jawline, eye shape, skin appearance and hairstyle direction.

- Listing: https://mcp.tc/i/ilook-face-analysis
- Connect: use the server's own URL `https://www.ilook.fit/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: iLook
- Homepage: <https://www.ilook.fit/ai-agent-face-analysis-api>

## About

iLook Face Analysis takes one authorized adult photo and returns structured, descriptive feedback. A full report gives face shape, five subjective appearance scores and an approximate Golden Ratio phi score. Focused tools return a single measurement such as symmetry, jawline, canthal tilt, eye shape, facial ratios, color palette, skin appearance or hairstyle direction.

It runs as a hosted streamable HTTP endpoint. The MCP endpoint answers without sign-in. Every call requires an attestation that the person is an adult and the use is authorized. The service rejects missing faces, multiple faces, possible minors and unsupported images. It does not do identity matching or medical conclusions.

## What it can do

- Score a face photo with face shape, subscores and phi score
- Analyze face shape and get styling direction
- Rate jawline definition and balance
- Measure facial symmetry and facial ratios
- Check canthal tilt and eye shape
- Describe skin appearance and color palette cues
- Suggest hairstyle direction based on face shape

## Tools (14)

- `score_face`: Face shape context, five subjective scores and approximate phi score for one photo. (read-only)
- `analyze_face_shape`: Face shape, runner-up shape, outline cues and styling direction. (read-only)
- `rate_jawline`: Visible jawline definition, balance and lower-face cues. (read-only)
- `analyze_canthal_tilt`: Left, right and average eye-corner tilt cues. (read-only)
- `detect_eye_shape`: Eye opening shape, corner orientation and framing. (read-only)
- `analyze_adult_face_age_cues`: Broad adult presentation cues, not an exact age. (read-only)
- `analyze_facial_symmetry`: Left-right symmetry cues across visible features. (read-only)
- `analyze_golden_ratio_face`: Approximate Golden Ratio phi score and proportion cues. (read-only)
- `run_attractiveness_test`: Subjective appearance score with its visible basis. (read-only)
- `analyze_psl_score`: Broad PSL-style range from visible geometry. (read-only)
- `calculate_facial_ratios`: Face-ratio and spacing cues from one photo. (read-only)
- `analyze_color_palette`: Style-oriented palette, contrast and lighting cues. (read-only)
- `analyze_skin_appearance`: Appearance-only texture, evenness and shine cues. (read-only)
- `find_hairstyle_direction`: Hairstyle and framing direction based on face shape. (read-only)

## Example prompts

- "Analyze the face shape in this photo and suggest a hairstyle direction."
- "Check the facial symmetry of this portrait. I confirm I am an adult and authorized."
- "Give me the Golden Ratio phi score for this profile photo."
- "Which color palette suits the lighting and contrast in this picture?"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http ilook-face-analysis https://www.ilook.fit/mcp
```

2. Start Claude Code and type `/mcp`. **ilook-face-analysis** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **iLook Face Analysis** and paste this URL:

```url
https://www.ilook.fit/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=iLook%20Face%20Analysis&connectorUrl=https%3A%2F%2Fwww.ilook.fit%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://www.ilook.fit/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://www.ilook.fit/mcp` as the server URL and choose **No authentication**.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=ilook-face-analysis&config=eyJ1cmwiOiJodHRwczovL3d3dy5pbG9vay5maXQvbWNwIn0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "ilook-face-analysis": {
      "url": "https://www.ilook.fit/mcp"
    }
  }
}
```

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=ilook-face-analysis&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fwww.ilook.fit%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"ilook-face-analysis","type":"http","url":"https://www.ilook.fit/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "ilook-face-analysis": {
      "type": "http",
      "url": "https://www.ilook.fit/mcp"
    }
  }
}
```

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "ilook-face-analysis": {
      "serverUrl": "https://www.ilook.fit/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add ilook-face-analysis --url https://www.ilook.fit/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.ilook-face-analysis]
url = "https://www.ilook.fit/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http ilook-face-analysis https://www.ilook.fit/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "ilook-face-analysis": {
      "type": "http",
      "url": "https://www.ilook.fit/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://www.ilook.fit/mcp`.

## Recent changes

- 2026-10-16 19:25 UTC: Tracking started: 14 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/ilook-face-analysis#history (Atom feed: https://mcp.tc/i/ilook-face-analysis/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.4.0
- MCP protocol version: 2025-11-25
- Last checked: 2026-10-24 (reachable)
- Listed: 2026-10-16
- Updated: 2026-10-16

---
Source: https://mcp.tc/i/ilook-face-analysis (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report