Skip to content
OpenMicroDrama

MiniMax-AI /MiniMax-MCP

Plugs MiniMax speech, voice cloning, image and video tools into your MCP client
Model toolingMITEnglish README
Open on GitHubSave

About MiniMax-MCP

MiniMax-MCP is MiniMax's official MCP server, which plugs their AI tools into your app. MCP is a standard way to give AI apps extra tools. It adds text-to-speech, voice cloning, voice design, image and video generation. You need a paid MiniMax API key, and the key and host must match regions.

Best for: Agent users who already work in an MCP client and want MiniMax speech, image and video tools inside it.

What it does

  • Turns text into speech with any voice from the list
  • Clones a voice from audio files you provide
  • Designs a new voice from a written description
  • Makes images and videos from prompts
  • Checks video jobs with query_video_generation
  • Returns files as URLs or downloads them locally

Quickstart

Rewritten from the README. Check the repo for the latest steps.

  1. 1
    Get an API key from MiniMax for your region (global or mainland).
  2. 2
    Install uv: the command below
    curl -LsSf https://astral.sh/uv/install.sh | sh
  3. 3
    Add a MiniMax entry to your MCP client config, with uvx minimax-mcp -y as the command.
  4. 4
    Set MINIMAX_API_KEY, MINIMAX_MCP_BASE_PATH and MINIMAX_API_HOST in the env block. Keep key and host in the same region.
  5. 5
    Restart the client. On Windows, turn on Developer Mode in Claude Desktop first.

Models and languages

Models it works with

  • MiniMax-Hailuo-02

Interface and docs

  • English
  • Chinese

Alternatives

Other model tooling projects people compare with MiniMax-MCP.

MiniMax-AI

cli

MiniMax images, video, speech and text from your terminal

Model tooling
  • MiniMax H3
  • Hailuo-2.3
  • MiniMax-M3
  • +1
- GitHub starsNo license

letorig

video-generator-client

Puts Seedance, Kling, MiniMax and Wan video models behind one Python tool

Model tooling
  • Seedance 2.5
  • Seedance 2.0
  • Kling 3.0
  • +7
- GitHub starsMIT

higgsfield-ai

cli

40+ Higgsfield image, video, 3D and audio models from your terminal

Model tooling
  • Nano Banana Pro
  • Nano Banana 2 Lite
  • Gemini Omni Flash
  • +7
- GitHub starsMIT

Wan-Video

Wan2.2

Open video models for text, image, speech and character animation

Model tooling
  • Wan 2.2-T2V-A14B
  • Wan 2.2-I2V-A14B
  • Wan 2.2-TI2V-5B
  • +5
- GitHub starsApache-2.0

Featured on OpenMicroDrama

Do you maintain MiniMax-MCP? Add this badge to your README so English speakers can find our write-up.

Featured on OpenMicroDrama
markdown
[![Featured on OpenMicroDrama](https://openmicrodrama.com/badges/featured.svg)](https://openmicrodrama.com/projects/minimax-ai-minimax-mcp)

The badge links to this page. Want your description changed? Email support@openmicrodrama.com.

Reviewed Oct 1, 2026. Official MiniMax repo. Its README recommends a separate MiniMax CLI (mmx-cli) with newer models and more features. We write these descriptions ourselves. The repo's own docs are the final word.