mcp-minimax-music

This MCP server provides AI-powered music generation capabilities via the MiniMax Music API. It integrates with MCP hosts (such as Claude Desktop) to allow agents to generate music and audio content from text prompts, with support for a two-step generation process: submit a generation request and poll for status until the final audio is available. The server exposes a tool named generate_audio, which accepts a prompt, optional model parameter (defaulting to minimax-music), optional reference_audio_url for style matching, and an optional generation_id for status checks. You can fetch a resulting audio file when the generation completes, receiving a structured response that includes a status, an identifier, and a downloadable audio URL. Ensure you provide your API key securely, typically via environment variables, so requests to the MiniMax Music API are authenticated.

Prerequisites:

• Node.js v16 or higher
• npm (comes with Node.js)
• Access to Claude Desktop (optional, for config)

Installation steps:

1. Clone the repository: git clone https://github.com/yourusername/mcp-minimax-music-server.git cd mcp-minimax-music-server

2. Install dependencies: npm install

3. Build the server: npm run build

4. Run the server (example): npm start

Notes:

• The server expects an API key for AIML, typically provided via environment variables or the hosting platform's configuration. Ensure your environment has AIML_API_KEY set if running directly.

Tips and common considerations:

• Environment variable: AIML_API_KEY should be set to a value like 'Bearer <your-key>' and provided securely in your Claude Desktop config or hosting environment.
• Windows users configuring Claude Desktop should use double backslashes in file paths and point to the built index.js, e.g., build/index.js.
• If you encounter authentication errors, verify the API key format and that it is correctly mounted into the process environment.
• The server relies on the MiniMax Music API; ensure network access to the API endpoints and that the API key has the necessary permissions.
• When testing, you can use generation_id to poll for status updates and retrieve the final audio URL when complete.