Mcp Face Transform

io.github.AceDataCloudv2026.9.30.0更新於 Oct 3, 2026

AceDataCloud Face Transform MCP: keypoints, beautify, age/gender, swap, cartoon, liveness

已驗證Streamable HTTP可網頁執行AI & MLMedia & Design

概覽

AI 產生的概覽

讓助理呼叫 AceDataCloud 人臉影像能力：關鍵點偵測、美顏、年齡或性別轉換、換臉、卡通化以及活體偵測。

功能
把 AceDataCloud Face Transform API 包裝成 MCP 工具。工具涵蓋每張人臉 90 多個關鍵點的偵測、美顏（磨皮、美白、瘦臉、放大眼睛）、年齡與性別轉換、來源圖與目標圖之間的換臉、卡通化，以及活體偵測。另有一個回傳用戶端使用說明的工具。換臉可選擇使用非同步 webhook。
適用情境
適合助理需要分析或編輯人像照片的情境：擷取臉部關鍵點、修圖、產生年齡或性別版本、換臉、卡通風格化，或判斷照片是真人拍攝還是翻拍列印品或螢幕。
執行需求
需要 AceDataCloud API 權杖，透過環境變數 ACEDATACLOUD_API_TOKEN 提供（託管端點則使用 bearer 權杖）。可作為遠端 streamable HTTP 端點執行，也可用 uvx/pip 在本機以 Python 執行。需要連線至 AceDataCloud API 的網路。
安裝前請注意
需要 ACEDATACLOUD_API_TOKEN 密鑰，該密鑰會傳送給 AceDataCloud。影像會上傳到第三方服務處理，應避免使用敏感或私人照片。換臉、年齡/性別轉換與卡通化會產生被修改的人像，可能涉及肖像同意與濫用風險。README 說明所有 Face API 均處於 Alpha 階段，介面可能變動。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Mcp Face Transform，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "mcp-face-transform": {
      "type": "http",
      "url": "https://face.mcp.acedata.cloud/mcp"
    }
  }
}

README

MCP Face Transform Server

A Model Context Protocol (MCP) server that exposes the AceDataCloud Face Transform API — face keypoint detection, beautification, age/gender transform, face swap, cartoonization, and liveness detection.

Status: All Face APIs are currently in Alpha. Interfaces may evolve.

Features

  • Keypoint detection — 90+ landmarks per face, multi-face supported
  • Beautification — smoothing, whitening, face slimming, eye enlarging
  • Age transform — age or de-age a portrait
  • Gender transform — swap perceived facial gender characteristics
  • Face swap — move a source face onto a target image (with optional async webhook)
  • Cartoonize — render a portrait in animated / cartoon style
  • Liveness detection — distinguish live captures from printed / screen photos

Installation

bash
pip install mcp-face-transform

Configuration

Set your AceDataCloud API token:

bash
export ACEDATACLOUD_API_TOKEN=your_token_here

Get your token from https://platform.acedata.cloud.

Usage

stdio mode (default)

bash
mcp-face-transform

HTTP mode

bash
mcp-face-transform --transport http --port 8000

Tool Reference

ToolDescription
face_detect_keypointsDetect 90+ keypoints per face (multi-face supported).
face_beautifySmoothing, whitening, face slimming, and eye enlarging.
face_change_ageAge or de-age a portrait.
face_change_genderSwap perceived facial gender characteristics.
face_swapMove a source face onto a target image (with optional async webhook).
face_cartoonizeRender a portrait in cartoon / animated style.
face_detect_livenessDistinguish a live capture from a printed / screen photo.
face_get_usage_guideConcise client-side tool usage reference.

Example

text
"Detect all faces in https://example.com/group.jpg and return their keypoints."→ face_detect_keypoints(image_url="https://example.com/group.jpg")
"Lighten and smooth my portrait."→ face_beautify(image_url="https://example.com/me.jpg", smoothing=15, whitening=25)
"Replace the face in the scene with the headshot."→ face_swap(    source_image_url="https://example.com/headshot.jpg",    target_image_url="https://example.com/scene.jpg",  )

Configuration in Claude Desktop / Claude Code

json
{  "mcpServers": {    "face-transform": {      "command": "uvx",      "args": ["mcp-face-transform"],      "env": {        "ACEDATACLOUD_API_TOKEN": "your_api_token_here"      }    }  }}

Or use the hosted endpoint with bearer auth:

json
{  "mcpServers": {    "face-transform": {      "url": "https://face.mcp.acedata.cloud/mcp",      "headers": {        "Authorization": "Bearer your_api_token_here"      }    }  }}

Development

bash
pip install -e ".[dev,test]"pytest --cov=core --cov=toolsruff check .

Service details

Service details

License

MIT — see LICENSE.

來源：README.md，提交 f237b31

工具

0
工具後設資料尚未被收錄。

版本歷史

3
  1. v2026.9.30.0最新Sep 30, 2026
  2. v2026.9.29.0Sep 29, 2026
  3. v2026.8.23.0Sep 16, 2026