mcp-minimax
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ACEDATACLOUD_API_TOKEN | Yes | Your AceDataCloud API token |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| minimax_list_modelsB | Describe the MiniMax H3 model and supported input modes. |
| minimax_list_actionsA | List MiniMax H3 generation and task tools. |
| minimax_list_tasksA | List video generation tasks, optionally filtered by creation timestamp. |
| minimax_get_taskA | Query the status and result of a video generation task. |
| minimax_get_tasks_batchA | Query multiple video generation tasks at once. |
| minimax_delete_taskB | Delete a MiniMax video generation task. |
| minimax_generate_video_from_textB | Generate a MiniMax H3 video from a text prompt. |
| minimax_generate_video_from_imagesA | Generate from one first-frame image or multiple reference images. |
| minimax_generate_video_from_audioA | Generate a MiniMax H3 video guided by audio and reference images. |
| minimax_generate_videoD | Generate a video from the full MiniMax content schema. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| minimax_video_generation_guide | Guide tool selection for MiniMax H3 video generation. |
| minimax_workflow_examples | Show common MiniMax H3 workflows. |
| minimax_prompt_suggestions | Provide MiniMax H3 prompt-writing guidance. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool targets a distinct operation: discovery (list_models, list_actions), task management (list_tasks, get_task, get_tasks_batch, delete_task), and generation (text/images/audio/full schema). Even the similar generation tools are clearly separated by input type and explicit mode constraints.
All tools follow a strict snake_case verb_noun pattern with a consistent 'minimax_' prefix. The pattern is uniform: list_*, get_*, delete_*, generate_video_from_*. Minor differences like get_tasks_batch still match the convention.
Ten tools is well-scoped for a video generation server. Each tool covers a necessary part of the workflow—discovery, generation (four input modes), tracking, and deletion—without redundant or superfluous entries.
The tool surface provides complete lifecycle coverage: describe capabilities, generate videos from all supported input types, query single/batch tasks, and delete tasks. No obvious dead ends or missing critical operations for the stated domain.