# minimax-mcp

Official MiniMax Model Context Protocol (MCP) server enabling seamless access to high-quality Text-to-Speech, voice cloning, image generation, and video generation tools for MCP-compatible AI clients like Claude Desktop, Cursor, and more.

Canonical URL: https://a2a-mcp.org/entry/minimax-mcp

Language: en

Category: MCP Servers

Updated: 2026-03-18

## Overview

**minimax-mcp** is the official Python implementation of the Model Context Protocol (MCP) server from MiniMax. It provides a standardized way for AI applications and clients to access MiniMax’s advanced multimodal generative capabilities through the MCP interface.

It supports high-quality Text-to-Speech (TTS), voice cloning, text-to-image, and text-to-video (including image-to-video) generation, making it easy to add rich media features to compatible AI tools.

## Key Features

- **Multimodal Tools**: Text-to-Speech, voice cloning, image generation, and video generation powered by MiniMax APIs.
- **Transports**: stdio (default for local use) and SSE.
- **Easy Setup**: Run via `uvx minimax-mcp` after setting your `MINIMAX_API_KEY`.
- **Client Support**: Works with Claude Desktop, Cursor, Windsurf, OpenAI Agents, and other MCP-compatible clients.
- **Self-Hostable**: Run locally for privacy and low latency.
- **Official Maintenance**: Developed and supported by MiniMax-AI.

A JavaScript/TypeScript version is also available: [MiniMax-MCP-JS](https://github.com/MiniMax-AI/MiniMax-MCP-JS).

## Quick Start

1. Get a MiniMax API key from [platform.minimax.io](https://platform.minimax.io).
2. Install [uv](https://astral.sh/uv).
3. Add the server to your MCP client configuration (e.g. Claude Desktop `mcp.json`):

```json
{
  "mcpServers": {
    "MiniMax": {
      "command": "uvx",
      "args": ["minimax-mcp"],
      "env": {
        "MINIMAX_API_KEY": "sk-..."
      }
    }
  }
}
```

The server will then be automatically available to your AI client.

## Use Cases

- Generating images or videos directly from natural language prompts inside coding or chat interfaces.
- Adding realistic voice output and custom voice cloning to AI assistants.
- Building multimodal AI agents that combine text, audio, and visual generation.
- Rapid prototyping of creative workflows with professional-grade media tools.

## Resources

- Python Repository: https://github.com/MiniMax-AI/MiniMax-MCP
- JavaScript Version: https://github.com/MiniMax-AI/MiniMax-MCP-JS
- Official MCP Guide: https://platform.minimax.io/docs/guides/mcp-guide
- Model Context Protocol: https://modelcontextprotocol.io

**Note**: This is the core multimodal MCP server. A separate `MiniMax-Coding-Plan-MCP` exists for coding-specific web search and image understanding tools.

## Tags

- mcp
- mcp-server
- minimax
- tts
- text-to-speech
- voice-cloning
- image-generation
- video-generation
- multimodal
- python
- ai

## Sources

- [Project website](https://github.com/MiniMax-AI/MiniMax-MCP)