The mcp-minimax server enables multimodal video generation using the MiniMax H3 model. It supports:
Video generation:
Text-to-video: Generate from a detailed prompt.
Image-to-video: Animate 1–9 reference images, with optional motion guidance.
Audio-to-video: Create videos driven by 1–3 audio clips, with optional image guidance.
Full schema generation: Submit a raw content schema for maximum control.
Video options: 4–15 sec duration, 16:9 or 9:16 aspect ratio, optional callback URL.
Task management:
Query a single task's status and results.
Batch query multiple tasks (up to ~50).
Delete a task.
Discovery: List model details and supported input modes; list all available tools.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-minimax Generate a 6-second video of a cat exploring a neon city at night"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol server for MiniMax H3 multimodal video generation through AceDataCloud.
Text-to-video
Image-, video-, and audio-guided video generation
4–15 second output in 768P or 2K, with adaptive, landscape, portrait, and square ratios
Asynchronous task retrieval, batch retrieval, and deletion
Hosted OAuth HTTP transport and local stdio transport
Related MCP server: minimax-omni
Tool | Purpose |
| Generate from a detailed prompt |
| Generate from one to nine image URLs |
| Generate with one to three audio URLs and required images |
| Generate from the full documented content schema |
| List tasks with optional timestamp filters |
| Retrieve one task |
| Retrieve several tasks |
| Delete one task |
| Show model constraints |
| Show available workflows |
https://minimax.mcp.acedata.cloud/mcpThe hosted server supports AceDataCloud OAuth. MCP clients that support remote OAuth can connect directly to this URL.
Public API reference: MiniMax H3 Videos API.
pipx install mcp-minimax
export ACEDATACLOUD_API_TOKEN="YOUR_API_TOKEN"
mcp-minimaxGet a token from AceDataCloud.
claude mcp add minimax --transport stdio \
--env ACEDATACLOUD_API_TOKEN=YOUR_API_TOKEN \
-- mcp-minimax{
"mcpServers": {
"minimax": {
"command": "mcp-minimax",
"env": {
"ACEDATACLOUD_API_TOKEN": "YOUR_API_TOKEN"
}
}
}
}Text:
Generate a 6-second 16:9 video: a red fox running through a snowy forest at dawn, low tracking shot.Images:
Animate these two reference images for 8 seconds while preserving the character and clothing.Audio:
Create a 9:16 dance video guided by this audio, with cuts and motion following the beat.Generation tools submit asynchronously. Poll the returned task ID with minimax_get_task until the final AceDataCloud CDN video is available.
pip install -e ".[dev,test]"
ruff check .
pytest --cov=core --cov=tools
mypy core toolsMIT
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Hailuo (MiniMax) AI video generation
MCP server for Wan AI video generation
MCP server for Kling AI video generation
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AceDataCloud/MinimaxMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server