The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the MCP Minimax listing page.
Model Context Protocol server for MiniMax H3 multimodal video generation through AceDataCloud.
| Tool | Purpose |
|---|---|
minimax_generate_video_from_text | Generate from a detailed prompt |
minimax_generate_video_from_images | Generate from one to nine image URLs |
minimax_generate_video_from_audio | Generate with one to three audio URLs and required images |
minimax_generate_video | Generate from the full documented content schema |
minimax_list_tasks | List tasks with optional timestamp filters |
minimax_get_task | Retrieve one task |
minimax_get_tasks_batch | Retrieve several tasks |
minimax_delete_task | Delete one task |
minimax_list_models | Show model constraints |
minimax_list_actions | Show available workflows |
The hosted server supports AceDataCloud OAuth. MCP clients that support remote OAuth can connect directly to this URL.
Public API reference: MiniMax H3 Videos API.
Get a token from AceDataCloud.
Text:
Images:
Audio:
The HTTP API waits for completion by default, while MCP generation tools default async to true so agents receive a task ID immediately. Poll it with minimax_get_task until the final AceDataCloud CDN video is available. Set async=false only when the client can safely wait for the complete result.
MIT