Connection check
local install
minimax-mcp-js
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
Tools
20
GitHub stars
128
Installs / wk
658
Licence
MIT
Transport
stdio
Last checked
never
Tools & capabilities
20 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
async_mode
from source
Whether to use async mode. Defaults to False. If True, the video generation task will be submitted asynchronously and the response will return a task_id. Should use Whether to use async mode. Defaults to False. If True, the video generation task will be submitted asynchronously and the response will return a task_id. Should use
bitrate
from source
Bitrate (bps), values: [64000, 96000, 128000, 160000, 192000, 224000, 256000, 320000] Bitrate (bps), values: [64000, 96000, 128000, 160000, 192000, 224000, 256000, 320000]
channel
from source
Audio channels, values: [1, 2] Audio channels, values: [1, 2]
duration
from source
The duration of the video. The model must be The duration of the video. The model must be
emotion
from source
Speech emotion, values: [ Speech emotion, values: [
format
from source
Audio format, values: [ Audio format, values: [
generate_video
from source
Generate video based on text prompt Generate video based on text prompt
image_to_video
from source
Generate video based on image Generate video based on image
list_voices
from source
List all available voices List all available voices
model
from source
Model to use Model to use
pitch
from source
Speech pitch (-12 to 12) Speech pitch (-12 to 12)
play_audio
from source
Play audio file. Supports WAV and MP3 formats. Does not support video. Play audio file. Supports WAV and MP3 formats. Does not support video.
query_video_generation
from source
Query the status of a video generation task. Query the status of a video generation task.
resolution
from source
The resolution of the video. The model must be The resolution of the video. The model must be
speed
from source
Speech speed (0.5-2.0) Speech speed (0.5-2.0)
text_to_audio
from source
Convert text to audio Convert text to audio
text_to_image
from source
Generate image based on text prompt Generate image based on text prompt
voice_clone
from source
Clone voice using provided audio file Clone voice using provided audio file
voice_design
from source
Generate a voice based on description prompts Generate a voice based on description prompts
vol
from source