MCP Hub
Back to servers

Magic Hour MCP Server

Enables AI-powered media manipulation including face swapping for videos and photos, lip syncing, and face detection via the Magic Hour AI platform. It provides tools for uploading files, managing video projects, and processing content from both local files and YouTube URLs.

glama
Updated
Mar 10, 2026

Magic Hour MCP Server

MCP server for Magic Hour AI — face swap videos, face swap photos, lip sync, face detection, and file management.

Tools

ToolDescription
face_swap_videoSwap a face onto a video (file/URL source)
face_swap_video_youtubeSwap a face onto a YouTube video
face_swap_video_individualSwap specific faces using face detection IDs
face_swap_photoSwap a face onto a photo
detect_facesDetect faces in an image or video
get_face_detection_resultGet detected face IDs and URLs
lip_syncSync lip movements to an audio track
upload_fileUpload a file to Magic Hour storage
get_video_project_statusCheck video project status and get download URLs
get_image_project_statusCheck image project status and get download URLs
delete_video_projectDelete a video project
delete_image_projectDelete an image project

Setup

  1. Get an API key from magichour.ai/settings/developer

  2. Install dependencies:

npm install
  1. Build:
npm run build

Claude Desktop Configuration

Add to ~/.claude/claude_desktop_config.json:

{
  "mcpServers": {
    "magic-hour": {
      "command": "node",
      "args": ["/path/to/magic-hour-mcp/dist/index.js"],
      "env": {
        "MAGIC_HOUR_API_KEY": "mhk_live_your_key_here"
      }
    }
  }
}

Claude Code Configuration

Add to ~/.claude/settings.json:

{
  "mcpServers": {
    "magic-hour": {
      "command": "node",
      "args": ["/path/to/magic-hour-mcp/dist/index.js"],
      "env": {
        "MAGIC_HOUR_API_KEY": "mhk_live_your_key_here"
      }
    }
  }
}

Usage Example

Face swap a dance video:
1. Upload your face image: upload_file → get file_path
2. Start face swap: face_swap_video with video URL + face file_path
3. Poll status: get_video_project_status until "complete"
4. Download from the returned URL

Individual face swap:
1. Detect faces: detect_faces on the source video
2. Get results: get_face_detection_result to see all faces
3. Swap specific faces: face_swap_video_individual with face mappings

License

MIT

Reviews

No reviews yet

Sign in to write a review