MiniMax
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
claude mcp add --transport stdio minimax-ai-minimax-mcp uvx minimax-mcp -y \ --env MINIMAX_API_KEY="insert-your-api-key-here" \ --env MINIMAX_API_HOST="https://api.minimax.io | https://api.minimaxi.com" \ --env MINIMAX_MCP_BASE_PATH="local-output-dir-path, such as /User/xxx/Desktop" \ --env MINIMAX_API_RESOURCE_MODE="optional, [url|local], url is default, audio/image/video are downloaded locally or provided in URL format"
How to use
MiniMax MCP server exposes a set of tools that let MCP clients interact with MiniMax APIs for text-to-speech, voice cloning, video generation, and image generation. The server can communicate via standard MCP transports such as stdio (when running locally) or SSE (when deployed in the cloud) to enable seamless integration with clients like Claude Desktop, Cursor, Windsurf, and OpenAI Agents. To use it, configure the MiniMax MCP server in your MCP client (for example Claude Desktop) with the provided uvx-based command and environment variables. Once configured, you can request speech synthesis, voice cloning, video generation, and image generation through the MCP interface, with the API key and host region matching your MiniMax account and region. The transport layer handles the data flow, delivering audio or media outputs back to the client.
How to install
Prerequisites:
- Python 3.8+ (recommended)
- A working internet connection
- Access to the MiniMax API (API key and host)
Installation steps:
- Install uv (Python package manager) if you do not have it:
- Run the recommended installer from the uv project: curl -LsSf https://astral.sh/uv/install.sh | sh
- Ensure uv is available on your PATH by restarting your terminal.
- Install the MiniMax MCP package using uvx:
- uvx minimax-mcp -y This installs the MiniMax MCP server package and makes the minimax-mcp command available.
- Prepare your configuration for Claude Desktop or other MCP clients:
- Use the JSON configuration shown in mcp_config (under the MiniMax server entry) and place it into the client’s MCP server configuration field.
- Run and verify:
- Start the MCP server (if not auto-started by the client) with: uvx minimax-mcp -y
- Ensure the environment variables (MINIMAX_API_KEY, MINIMAX_API_HOST, etc.) are set as described in the mcp_config section.
- In your MCP client, point to the configured MiniMax server entry and test a simple request to confirm TTS, voice cloning, or media generation works as expected.
Additional notes
Tips and caveats:
- Make sure MINIMAX_API_KEY matches the host given by MINIMAX_API_HOST; mismatches can trigger API key errors. If you see 'API Error: invalid api key', verify both the key and the host region.
- MINIMAX_API_RESOURCE_MODE controls how media resources are handled; default is URL-based resources, but you can switch to local downloads if needed.
- MINIMAX_MCP_BASE_PATH should point to a writable directory for local output when using local resource mode.
- If using Claude Desktop on Windows, you may need to enable Developer Mode as described in the Claude Desktop guide to allow MCP server integration.
- The server supports two transports: stdio (local/deployment) and SSE (cloud deployment). Choose the transport that matches your deployment scenario.
- For region-specific hosts, ensure you set MINIMAX_API_HOST to the correct endpoint (Global: https://api.minimax.io, Mainland: https://api.minimaxi.com).
Related MCP Servers
edumcp
EDUMCP is a protocol that integrates the Model Context Protocol (MCP) with applications in the education field, dedicated to achieving seamless interconnection and interoperability among different AI models, educational applications, smart hardware, and teaching AGENTs.
cursor-notebook
Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files
MiniMax -JS
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.
furi
CLI & API for MCP management
PixVerse
Official PixVerse Model Context Protocol (MCP) server that enables interaction with powerful AI video generation APIs.
mcp-veo2
MCP for Video- or Image-Generation with Google VEO2