Quickstart

Updated 2026-10-17

Connect an AI assistant to the face measurement data, check it works, then use the dataset and the widget. No account and no API key are needed for any step.

1. Connect your assistant

The hosted server works in every client that supports remote MCP servers. Claude Code is one command:

claude mcp add --transport http --scope user thefaceanalysis https://mcp.thefaceanalysis.com/mcp

For other clients use the same URL: https://mcp.thefaceanalysis.com/mcp. Step-by-step pages: Claude Code, Claude (claude.ai and Desktop), Claude Desktop (local), ChatGPT, Codex, Cursor, VS Code, Gemini CLI, Any other client.

2. Ask a question

Using The Face Analysis, what is the median fWHR across your 102 reference faces?

The answer should be 1.78, the median fWHR across the 102 reference faces, returned by the get_reference_statistics tool.

3. Check without a client

curl -s https://mcp.thefaceanalysis.com/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

https://mcp.thefaceanalysis.com/health answers ok. The server is stateless and accepts only POST /mcp, so a browser visit to /mcp shows 405.

4. Use the data directly

npm install thefaceanalysis-data

import { median } from "thefaceanalysis-data";
median("fwhr"); // 1.78

Files, columns and examples in Python and R are on the dataset page.

5. Put the widget on a page

<div data-tfa-widget="face-shape" data-size="standard"></div>
<script async src="https://thefaceanalysis.com/embed.js"></script>

Sizes, the npm and React versions and the terms are on the embed page.