Magic Hour MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAGIC_HOUR_API_KEY | Yes | Your Magic Hour API key, which can be obtained from magichour.ai/settings/developer |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| face_swap_videoB | Swap a face onto a video. Provide a source video (file path or URL) and a face image. Returns the project ID to check status. |
| face_swap_video_youtubeB | Swap a face onto a YouTube video. Provide a YouTube URL and a face image. |
| face_swap_photoC | Swap a face onto a photo. Provide a target photo and a source face image. |
| detect_facesC | Detect faces in an image or video. Returns face IDs that can be used for individual face swapping. |
| get_face_detection_resultB | Get the result of a face detection job. Returns detected face IDs and URLs. |
| face_swap_video_individualA | Swap specific faces in a video. Use detect_faces first to get face IDs, then map each original face to a new face image. |
| lip_syncC | Sync lip movements in a video to an audio track. Provide a video and audio file. |
| get_video_project_statusB | Check the status of a video project (face swap, lip sync, etc). Returns status, download URLs when complete. |
| get_image_project_statusA | Check the status of an image project (face swap photo, etc). Returns status, download URLs when complete. |
| upload_fileA | Upload a local file to Magic Hour for use in other tools. Returns the file path to use in subsequent API calls. |
| delete_video_projectC | Delete a video project. |
| delete_image_projectC | Delete an image project. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Most tools have distinct purposes, such as delete_image_project vs. delete_video_project, and face_swap_photo vs. face_swap_video. However, face_swap_video, face_swap_video_individual, and face_swap_video_youtube could cause confusion due to overlapping video face-swapping functionality, though descriptions help differentiate them.
Tool names follow a consistent snake_case pattern with clear verb_noun structures, such as delete_image_project, detect_faces, and get_face_detection_result. There are no deviations in naming conventions across all 12 tools.
With 12 tools, the server is well-scoped for its face-swapping and media processing domain. Each tool serves a specific role, from project management to face detection and lip syncing, without feeling excessive or insufficient.
The toolset covers core operations like creation (via face swap tools), retrieval (get status tools), deletion, and processing (detect, lip sync). A minor gap exists in update operations for projects, but agents can work around this by re-creating or managing projects through deletion and re-upload.