Koskamo

The Face Analysis MCP

A read-only MCP server that provides AI assistants with access to face measurement statistics, face type rules, methodology, and a face shape classifier based on a reference dataset of 102 faces. It requires no account or photo upload for the statistical lookups.

Visit Indiex

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

The Face Analysis MCP logo, by IndiexVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Indiex
MCP endpoint (Streamable HTTP)
https://mcp.thefaceanalysis.com/mcp
Vendor documentation

What you can do with it

  • Look up face measurement statistics from 102 reference faces
  • Read exact face shape rules and type definitions
  • Classify face shape from four facial distances

Source and maintenance

Vendor evidenceRegistry 0.1.0
mcp-registry: com.thefaceanalysis/face-analysis@0.1.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
thefaceanalysis 0.1.0
MCP protocol
2025-06-18
Tools
7 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

7 advertised

get_reference_statistics — Face measurement statistics
Advertised by the server during the last successful anonymous check.
Advertised read-only

Percentiles (p10, p25, median, p75, p90, min, max) of facial measurements from 102 adult faces (49 women, 53 men) of the Face Research Lab London Set, measured with a 478-point MediaPipe landmarker. Measures: composite score, symmetry, golden ratio fit, fWHR, midface ratio, pupillary distance, canthal tilt. Aggregates only; one research set photographed in one city, so these describe these faces, not a population.

get_reference_statistics input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "group": {
      "enum": [
        "all",
        "female",
        "male"
      ],
      "type": "string",
      "description": "all, female or male. Omit for all three."
    },
    "measure": {
      "enum": [
        "composite",
        "symmetry",
        "golden",
        "fwhr",
        "midface",
        "pd",
        "tilt"
      ],
      "type": "string",
      "description": "One measure. Omit for all."
    }
  },
  "additionalProperties": false
}
get_reference_statistics annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
list_face_types — List face, eye, lip and nose types
Advertised by the server during the last successful anonymous check.
Advertised read-only

Lists the types the site's detectors use, with slug, name, page URL and how many of the 102 reference faces each type covered. The split shows how the detector divides these faces, not how common a type is in a population.

list_face_types input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "category": {
      "enum": [
        "face",
        "eye",
        "lip",
        "nose"
      ],
      "type": "string",
      "description": "Omit for all four categories."
    }
  },
  "additionalProperties": false
}
list_face_types annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_face_type — Describe one face, eye, lip or nose type
Advertised by the server during the last successful anonymous check.
Advertised read-only

Definition and how the type is measured from a front photo (the exact threshold rule), plus its page URL. Example: category 'face', slug 'oval'.

get_face_type input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "category",
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "e.g. oval, heart, hooded, upturned"
    },
    "category": {
      "enum": [
        "face",
        "eye",
        "lip",
        "nose"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
get_face_type annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
classify_face_shape — Classify a face shape from four measurements
Advertised by the server during the last successful anonymous check.
Advertised read-only

Runs the same seven-rule face shape classifier as thefaceanalysis.com/face-shape-detector on four distances (any consistent unit: pixels, mm or landmark units). Returns the shape, the rule that matched and the four ratios. It does not look at photos: to measure a photo, use the widget (get_embed_snippet) or the site. Borderline faces can flip between two shapes; no accuracy figure is claimed because the reference set has no labelled face types.

classify_face_shape input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "face_length",
    "cheekbone_width",
    "forehead_width",
    "jaw_width"
  ],
  "properties": {
    "jaw_width": {
      "type": "number",
      "description": "Width across the jaw",
      "exclusiveMinimum": 0
    },
    "face_length": {
      "type": "number",
      "description": "Top of the forehead surface to the bottom of the chin",
      "exclusiveMinimum": 0
    },
    "forehead_width": {
      "type": "number",
      "description": "Width across the temples",
      "exclusiveMinimum": 0
    },
    "cheekbone_width": {
      "type": "number",
      "description": "Widest point across the cheekbones",
      "exclusiveMinimum": 0
    }
  },
  "additionalProperties": false
}
classify_face_shape annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_methodology — Methodology, thresholds and validity
Advertised by the server during the last successful anonymous check.
Advertised read-only

How the numbers are made: the landmark model, every classification threshold, how the 1-10 score is built, and how it correlated with 2,513 human raters on the same faces (it did not predict them). Includes the method change history.

get_methodology input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "include_changelog": {
      "type": "boolean",
      "description": "Also return the dated change history."
    }
  },
  "additionalProperties": false
}
get_methodology annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_citation — How to cite the data
Advertised by the server during the last successful anonymous check.
Advertised read-only

Citation text, license (CC BY 4.0 for the aggregate numbers) and the source photo set. Use when quoting a number.

get_citation input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
get_citation annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_embed_snippet — Embed code for the face shape widget
Advertised by the server during the last successful anonymous check.
Advertised read-only

HTML a website owner can paste to add the free face shape finder (it measures the visitor's photo in their browser, no sign-up). Includes the visible credit link the terms ask for.

get_embed_snippet input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "size": {
      "enum": [
        "compact",
        "standard",
        "wide"
      ],
      "type": "string",
      "description": "compact 360px, standard 480px, wide 720px"
    }
  },
  "additionalProperties": false
}
get_embed_snippet annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
851 ms
95th percentile latency
851 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 851 ms · metadata changed · 7 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http the-face-analysis-mcp https://mcp.thefaceanalysis.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add the-face-analysis-mcp --url https://mcp.thefaceanalysis.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable the-face-analysis-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "the-face-analysis-mcp": {
      "url": "https://mcp.thefaceanalysis.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "the-face-analysis-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.thefaceanalysis.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start the-face-analysis-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "the-face-analysis-mcp": {
      "type": "http",
      "url": "https://mcp.thefaceanalysis.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http the-face-analysis-mcp https://mcp.thefaceanalysis.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "the-face-analysis-mcp": {
      "url": "https://mcp.thefaceanalysis.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "the-face-analysis-mcp": {
      "serverUrl": "https://mcp.thefaceanalysis.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like The Face Analysis MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 3,922

Do you run The Face Analysis MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing