What can you do with this server?

The MiniMax MCP Server enables seamless interaction with MiniMax's APIs for: * Text-to-speech: Convert text to audio with customizable voice, speed, volume, and pitch * Voice cloning: Create new voices by cloning from audio files or URLs * List available voices: Retrieve pre-defined or cloned voices * Video generation: Create videos from text prompts with camera movement instructions * Image generation: Produce images from text prompts with customizable aspect ratios * Audio playback: Play WAV or MP3 files locally or from URLs * Task management: Query results or status of generation tasks

Which integrations are available for this server?

Provides Windsurf (by Codeium) with access to MiniMax's Text to Speech, voice cloning, and video/image generation APIs Provides integration with GitHub for accessing the MiniMax MCP server's codebase and repositories Connects to MiniMax's Hugging Face organization to access related models and resources Allows OpenAI Agents to use MiniMax's Text to Speech, voice cloning, and video/image generation capabilities Offers WeChat-based access to MiniMax's services through a QR code connection

How do I use MiniMax MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MiniMax MCP Server generate an image of a futuristic city at sunset" 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.

de en es ja ko ru zh

MiniMax MCP Server

Official

by MiniMax-AI

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

export

💡 Recommended: MiniMax CLI (mmx-cli) — our official command-line tool with the latest models and additional features including text, vision, and search. Works as an AI agent skill for Claude Code, Cursor, OpenClaw, etc.

Documentation

中文文档
MiniMax-MCP-JS - Official JavaScript implementation of MiniMax MCP

Related MCP server: MiniMax MCP

Quickstart with MCP Client

Get your API key from MiniMax.
Install uv (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh or see the uv repo for additional install methods.
Important: The API host and key vary by region and must match; otherwise, you'll encounter an Invalid API key error.

Region	Global	Mainland
MINIMAX_API_KEY	go get from MiniMax Global	go get from MiniMax
MINIMAX_API_HOST	https://api.minimax.io	https://api.minimaxi.com

Claude Desktop

Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:

{
  "mcpServers": {
    "MiniMax": {
      "command": "uvx",
      "args": [
        "minimax-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "insert-your-api-key-here",
        "MINIMAX_MCP_BASE_PATH": "local-output-dir-path, such as /User/xxx/Desktop",
        "MINIMAX_API_HOST": "api host, https://api.minimax.io | https://api.minimaxi.com",
        "MINIMAX_API_RESOURCE_MODE": "optional, [url|local], url is default, audio/image/video are downloaded locally or provided in URL format"
      }
    }
  }
}

⚠️ Warning: The API key needs to match the host. If an error "API Error: invalid api key" occurs, please check your api host:

Global Host：https://api.minimax.io
Mainland Host：https://api.minimaxi.com

If you're using Windows, you will have to enable "Developer Mode" in Claude Desktop to use the MCP server. Click "Help" in the hamburger menu in the top left and select "Enable Developer Mode".

Cursor

Go to Cursor -> Preferences -> Cursor Settings -> MCP -> Add new global MCP Server to add above config.

That's it. Your MCP client can now interact with MiniMax through these tools:

Transport

We support two transport types: stdio and sse.

stdio	SSE
Run locally	Can be deployed locally or in the cloud
Communication through `stdout`	Communication through `network`
Input: Supports processing `local files` or valid `URL` resources	Input: When deployed in the cloud, it is recommended to use `URL` for input

Available Tools

tool	description
`text_to_audio`	Convert text to audio with a given voice
`list_voices`	List all voices available
`voice_clone`	Clone a voice using provided audio files
`generate_video`	Generate a video from a prompt
`text_to_image`	Generate a image from a prompt
`query_video_generation`	Query the result of video generation task
`voice_design`	Generate a voice from a prompt using preview text

Release Notes

July 2, 2025

🆕 What's New

Voice Design: New voice_design tool - create custom voices from descriptive prompts with preview audio
Video Enhancement: Added MiniMax-Hailuo-02 model with ultra-clear quality and duration/resolution controls

📈 Enhanced Tools

voice_design - Generate personalized voices from text descriptions
generate_video - Now supports MiniMax-Hailuo-02 with 6s/10s duration and 768P/1080P resolution options

FAQ

1. invalid api key

Please ensure your API key and API host are regionally aligned

Region	Global	Mainland
MINIMAX_API_KEY	go get from MiniMax Global	go get from MiniMax
MINIMAX_API_HOST	https://api.minimax.io	https://api.minimaxi.com

2. spawn uvx ENOENT

Please confirm its absolute path by running this command in your terminal:

which uvx

Once you obtain the absolute path (e.g., /usr/local/bin/uvx), update your configuration to use that path (e.g., "command": "/usr/local/bin/uvx").

3. How to use `generate_video` in async-mode

Define completion rules before starting: Alternatively, these rules can be configured in your IDE settings (e.g., Cursor):

Example usage

⚠️ Warning: Using these tools may incur costs.

1. broadcast a segment of the evening news

2. clone a voice

3. generate a video

4. generate images

Available Tools

6 tools

generate_videoA

Generate a video from a prompt.

COST WARNING: This tool makes an API call to Minimax which may incur costs. Only use when explicitly requested by the user.

 Args:
    model (str, optional): The model to use. Values range ["T2V-01", "T2V-01-Director", "I2V-01", "I2V-01-Director", "I2V-01-live"]. "Director" supports inserting instructions for camera movement control. "I2V" for image to video. "T2V" for text to video.
    prompt (str): The prompt to generate the video from. When use Director model, the prompt supports 15 Camera Movement Instructions (Enumerated Values)
        -Truck: [Truck left], [Truck right]
        -Pan: [Pan left], [Pan right]
        -Push: [Push in], [Pull out]
        -Pedestal: [Pedestal up], [Pedestal down]
        -Tilt: [Tilt up], [Tilt down]
        -Zoom: [Zoom in], [Zoom out]
        -Shake: [Shake]
        -Follow: [Tracking shot]
        -Static: [Static shot]
    first_frame_image (str): The first frame image. The model must be "I2V" Series.
    output_directory (str, optional): The directory to save the video to.
Returns:
    Text content with the path to the output video file.

ParametersJSON Schema

Name	Required	Default
`model`	No	T2V-01
`prompt`	No
`output_directory`	No
`first_frame_image`	No

TDQS

A4.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses API call cost and model-specific behavior (camera instructions), but lacks info on rate limits, auth, or what gets destroyed. Adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with cost warning upfront and parameter details indented. Slightly lengthy but every part is useful; could be more concise but not overly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, description explains return value (path). All 4 parameters are described, and behavior for different models is covered. Complete for this tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, description fully explains all parameters: model values meaning, prompt camera instructions, first_frame_image for I2V, and output_directory. Adds substantial value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Generate a video from a prompt' with a specific verb and resource. It distinguishes from sibling tools (list_voices, play_audio, etc.) which handle audio or images, making video generation unique.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Includes a cost warning explicitly stating to use only when requested, plus details on when to choose Director vs I2V models. Provides clear context for appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_voicesA

List all voices available. Only supports when api_host is https://api.minimax.chat

Documentation

Quickstart with MCP Client

Claude Desktop

Cursor

Transport

Available Tools

Release Notes

July 2, 2025

🆕 What's New

📈 Enhanced Tools

FAQ

1. invalid api key

2. spawn uvx ENOENT

3. How to use generate_video in async-mode

Example usage

1. broadcast a segment of the evening news

2. clone a voice

3. generate a video

4. generate images

Available Tools

TDQS

3. How to use `generate_video` in async-mode