MiniMaxBLOCK
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.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
JavaScript/TypeScript implementation of MiniMax MCP, providing image generation, video generation, text-to-speech, and more.
<img alt="Homepage" src="https://img.shields.io/badge/_Homepage-MiniMax-FF4040?style=flat-square&labelColor=2C3E50&logo=data:image/svg+xml;base64,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&logoWidth=20" style="display: inline-block; vertical-align: middle;"/>
33c4da9aa322OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add minimax-mcp-js -- npx -y [email protected]
{
"mcpServers": {
"minimax-mcp-js": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (36)
36 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
aspectRatio | read | Image aspect ratio, values: [ |
async_mode | read | 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 |
audioFile | read | Audio file path |
bitrate | read | Bitrate (bps), values: [64000, 96000, 128000, 160000, 192000, 224000, 256000, 320000] |
channel | read | Audio channels, values: [1, 2] |
duration | read | The duration of the video. The model must be |
emotion | read | Speech emotion, values: [ |
firstFrameImage | read | First frame image |
format | read | Audio format, values: [ |
generate_video | read | Generate video based on text prompt |
image_to_video | read | Generate video based on image |
inputFilePath | read | Path to audio file to play |
isUrl | read | Whether audio file is a URL |
languageBoost | read | Enhance the ability to recognize specified languages and dialects. Supported values include: |
list_voices | read | List all available voices |
model | read | Model to use |
n | read | Number of images to generate (1-9) |
outputFile | read | Output file path, auto-generated if not provided |
pitch | read | Speech pitch (-12 to 12) |
play_audio | read | Play audio file. Supports WAV and MP3 formats. Does not support video. |
previewText | read | The text to preview the voice |
prompt | read | Text prompt for image generation |
promptOptimizer | read | Whether to optimize prompt |
query_video_generation | read | Query the status of a video generation task. |
resolution | read | The resolution of the video. The model must be |
sampleRate | read | Sample rate (Hz), values: [8000, 16000, 22050, 24000, 32000, 44100] |
speed | read | Speech speed (0.5-2.0) |
subtitleEnable | read | The parameter controls whether the subtitle service is enabled. The model must be |
text | read | Text to convert to audio |
text_to_audio | read | Convert text to audio |
text_to_image | read | Generate image based on text prompt |
voiceId | read | Voice ID to use, e.g. |
voiceType | read | Type of voices to list, values: [ |
voice_clone | read | Clone voice using provided audio file |
voice_design | read | Generate a voice based on description prompts |
vol | read | Speech volume (0.1-10.0) |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
|MINIMAX_API_HOST| https://api.minimaxi.chat (note the extra **"i"**) | https://api.minimax.chat |
|MINIMAX_API_HOST| https://api.minimaxi.chat (请注意额外的 **"i"** 字母) | https://api.minimax.chat |
.prettierignore
<img alt="Homepage" src="https://img.shields.io/badge/_Homepage-MiniMax-FF4040?style=flat-square&labelColor=2C3E50&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIH
<img alt="Chat" src="https://img.shields.io/badge/_MiniMax_Chat-FF4040?style=flat-square&labelColor=2C3E50&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHhtbG5zOn
<img alt="Homepage" src="https://img.shields.io/badge/_Homepage-MiniMax-FF4040?style=flat-square&labelColor=2C3E50&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIH
<img alt="Chat" src="https://img.shields.io/badge/_MiniMax_Chat-FF4040?style=flat-square&labelColor=2C3E50&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHhtbG5zOn
@chatmcp/sdk, @modelcontextprotocol/sdk, axios, cors, dotenv, express, zod, @types/cors
Gates applied: no_behavioural_pass.
33c4da9aa322full audit observations/trust-audit/mcp-server/minimax-ai__minimax-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 33c4da9aa322 | BLOCK | D | 69 | first audit |
Questions
What is the MiniMax MCP server?
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.
What tools does MiniMax expose?
36 in total: 36 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is MiniMax safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does MiniMax need?
No credential environment variables were found in its source, so it appears to need none.
How does MiniMax run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on npm as minimax-mcp-js at 0.0.18.
How current is this page?
The grade is for one exact copy of the source (33c4da9aa322), read on 2026-10-07. The repository is watched and re-audited when it changes.