{
  "markdown": "# MCP Face Transform Server\n\n<!-- mcp-name: io.github.AceDataCloud/mcp-face-transform -->\n\nA [Model Context Protocol](https://modelcontextprotocol.io) (MCP) server that\nexposes the AceDataCloud Face Transform API — face keypoint detection,\nbeautification, age/gender transform, face swap, cartoonization, and liveness\ndetection.\n\n> **Status:** All Face APIs are currently in **Alpha**. Interfaces may evolve.\n\n## Features\n\n- **Keypoint detection** — 90+ landmarks per face, multi-face supported\n- **Beautification** — smoothing, whitening, face slimming, eye enlarging\n- **Age transform** — age or de-age a portrait\n- **Gender transform** — swap perceived facial gender characteristics\n- **Face swap** — move a source face onto a target image (with optional async webhook)\n- **Cartoonize** — render a portrait in animated / cartoon style\n- **Liveness detection** — distinguish live captures from printed / screen photos\n\n## Installation\n\n```bash\npip install mcp-face-transform\n```\n\n## Configuration\n\nSet your AceDataCloud API token:\n\n```bash\nexport ACEDATACLOUD_API_TOKEN=your_token_here\n```\n\nGet your token from [https://platform.acedata.cloud](https://platform.acedata.cloud).\n\n## Usage\n\n### stdio mode (default)\n\n```bash\nmcp-face-transform\n```\n\n### HTTP mode\n\n```bash\nmcp-face-transform --transport http --port 8000\n```\n\n## Tool Reference\n\n| Tool | Description |\n|------|-------------|\n| `face_detect_keypoints` | Detect 90+ keypoints per face (multi-face supported). |\n| `face_beautify` | Smoothing, whitening, face slimming, and eye enlarging. |\n| `face_change_age` | Age or de-age a portrait. |\n| `face_change_gender` | Swap perceived facial gender characteristics. |\n| `face_swap` | Move a source face onto a target image (with optional async webhook). |\n| `face_cartoonize` | Render a portrait in cartoon / animated style. |\n| `face_detect_liveness` | Distinguish a live capture from a printed / screen photo. |\n| `face_get_usage_guide` | Concise client-side tool usage reference. |\n\n## Example\n\n```text\n\"Detect all faces in https://example.com/group.jpg and return their keypoints.\"\n→ face_detect_keypoints(image_url=\"https://example.com/group.jpg\")\n\n\"Lighten and smooth my portrait.\"\n→ face_beautify(image_url=\"https://example.com/me.jpg\", smoothing=15, whitening=25)\n\n\"Replace the face in the scene with the headshot.\"\n→ face_swap(\n    source_image_url=\"https://example.com/headshot.jpg\",\n    target_image_url=\"https://example.com/scene.jpg\",\n  )\n```\n\n## Configuration in Claude Desktop / Claude Code\n\n```json\n{\n  \"mcpServers\": {\n    \"face-transform\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-face-transform\"],\n      \"env\": {\n        \"ACEDATACLOUD_API_TOKEN\": \"your_api_token_here\"\n      }\n    }\n  }\n}\n```\n\nOr use the hosted endpoint with bearer auth:\n\n```json\n{\n  \"mcpServers\": {\n    \"face-transform\": {\n      \"url\": \"https://face.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer your_api_token_here\"\n      }\n    }\n  }\n}\n```\n\n## Development\n\n```bash\npip install -e \".[dev,test]\"\npytest --cov=core --cov=tools\nruff check .\n```\n\n## Service details\n\n<!-- canonical-documentation -->\n[Service details](https://platform.acedata.cloud/services/8efa1d83-9b75-4562-b44a-af95ce563d05)\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n",
  "bytes": 3263,
  "sha": "7c718d509d242f2fe6c87732ecbaab5722c8fbcf1ff0f5ccb1fb65e6cdf2adc9",
  "repo_slug": "acedatacloud/facetransformmcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_acedatacloud_mcp_face_transfor_fd61d8b4/readme"
}