# TheFaceAnalysis

TheFaceAnalysis supplies AI assistants with face shape classification rules and measurement percentiles across 102 faces without handling images.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: The-Face-Analysis
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/The-Face-Analysis/thefaceanalysis-mcp
- Updated: 2026-10-26
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/thefaceanalysis

## What it does

This server runs strictly in read-only mode and refuses image uploads. Instead of parsing photos, `classify_face_shape` accepts four pre-measured distances and applies seven sequential rules to identify the geometry. Handlers like `list_face_types` and `get_face_type` return explicit threshold values for lips, noses, eyes, and jawlines.

Through `get_reference_statistics`, your model reads distributions for midface ratios, fWHR, symmetry, and canthal tilt. These metrics come from 102 subjects in the Face Research Lab London Set. It also provides citation metadata under CC BY 4.0 alongside methodology verified against 2,513 human evaluators.

The server contains zero computer vision routines. You must extract coordinate distances elsewhere before querying these tools.

## Requirements
- Remote server: `https://mcp.thefaceanalysis.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http face-analysis https://mcp.thefaceanalysis.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add thefaceanalysis --url https://mcp.thefaceanalysis.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "thefaceanalysis": {
            "url": "https://mcp.thefaceanalysis.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "thefaceanalysis": {
            "type": "http",
            "url": "https://mcp.thefaceanalysis.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http thefaceanalysis https://mcp.thefaceanalysis.com/mcp
```

## When to use it
- Classify face geometry from four measured distances
- Retrieve percentile benchmarks for facial symmetry and fWHR
- Inspect numeric threshold rules for nose and eye categories
- Generate an embeddable widget snippet for web pages

## Example prompts
- Classify face shape using distances 140, 116, 124, and 185 with TheFaceAnalysis
- Show fWHR percentiles for male faces in the reference dataset
- Get the exact threshold rules used to categorize eye shapes

## Similar
- [zenodo-skill](https://affpapa.org/en/nevibecode/skills/zenodo-skill.md) — skill · 292 installs
- [dataset-curation](https://affpapa.org/en/nevibecode/skills/dataset-curation.md) — skill · 2600 installs
- [digital-health-clinical-asr-build](https://affpapa.org/en/nevibecode/skills/digital-health-clinical-asr-build.md) — skill · 1900 installs
- [tao-validate-dataset-format](https://affpapa.org/en/nevibecode/skills/tao-validate-dataset-format.md) — skill · 1600 installs
- [error-discovery](https://affpapa.org/en/nevibecode/skills/error-discovery.md) — skill · 1200 installs
- [arize-dataset](https://affpapa.org/en/nevibecode/skills/arize-dataset.md) — skill · 1100 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
