Sandbox
@MiniMax-AI/MiniMax-MCP

MiniMax MCP server for audio, image, and video APIs

This is a Python MCP server that lets an agent use MiniMax for speech, voice cloning, image generation, and video generation. It runs over stdio or SSE and is configured with your MiniMax API key and host.

1,578 starsβ€’282 forksβ€’Pythonβ€’Updated 28d ago
Who it's for

Builders who want their MCP client to generate speech, images, or video through MiniMax.

What it delivers

You can ask your agent to create media assets without leaving your MCP client.

What it does

Text to audio

Converts a prompt into speech with a selected voice using the `text_to_audio` tool.

Voice cloning

Uses uploaded audio to clone a voice with the `voice_clone` tool.

Voice design

Creates a custom voice from a text prompt and preview text with the `voice_design` tool.

Image generation

Generates images from prompts with the `text_to_image` tool.

Video generation

Creates videos from prompts and lets you check task status with `generate_video` and `query_video_generation`.

Voice listing

Lists the available voices with the `list_voices` tool.

MCP client support

Works with Claude Desktop, Cursor, Windsurf, OpenAI Agents, and other MCP clients over stdio or SSE.

How to get it

  1. 1Please confirm its absolute path by running this command in your terminal
    which uvx

README

export

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech and video/image generation APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to generate speech, clone voices, generate video, generate image and more.

πŸ’‘ Recommended: MiniMax CLI (mmx-cli) β€” 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

Quickstart with MCP Client

  1. Get your API key from MiniMax.
  2. 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.
  3. Important: The API host and key vary by region and must match; otherwise, you'll encounter an Invalid API key error.
RegionGlobalMainland
MINIMAX_API_KEYgo get from MiniMax Globalgo get from MiniMax
MINIMAX_API_HOSThttps://api.minimax.iohttps://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.

stdioSSE
Run locallyCan be deployed locally or in the cloud
Communication through stdoutCommunication through network
Input: Supports processing local files or valid URL resourcesInput: When deployed in the cloud, it is recommended to use URL for input

Available Tools

tooldescription
text_to_audioConvert text to audio with a given voice
list_voicesList all voices available
voice_cloneClone a voice using provided audio files
generate_videoGenerate a video from a prompt
text_to_imageGenerate a image from a prompt
query_video_generationQuery the result of video generation task
voice_designGenerate a voice from a prompt using preview text

Release Notes

July 2, 2025

πŸ†• 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

πŸ“ˆ 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

RegionGlobalMainland
MINIMAX_API_KEYgo get from MiniMax Globalgo get from MiniMax
MINIMAX_API_HOSThttps://api.minimax.iohttps://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

Files in the repo

Repository payloadβ€’13 top-level entries
  • .github
  • minimax_mcp
  • scripts
  • tests
  • .env.example
  • .gitignore
  • LICENSE
  • mcp_server_config_demo.json
  • pyproject.toml
  • README-CN.md
  • README.md
  • setup.py
  • uv.lock

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Open-source 3D architectural editor with a local CLI, MCP tools, and practical workflows for humans and AI agents.

23k
ahujasid/
blender-mcp

Community plugin to control Blender 3D with any LLM of your choice

28k

MCP server to provide Figma layout information to AI coding agents like Cursor

16k
grab/
cursor-talk-to-figma-mcp

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

7k
irinabuht12-oss/
google-meta-ads-ga4-mcp

Google Ads MCP + Meta Ads MCP + GA4 in one server for Claude, ChatGPT, Cursor & n8n β€” 250+ tools, hosted remote MCP, OAuth login, no API keys. By Ryze AI.

1.7k