Suno API and MCP: how to add music generation to your project

Suno is a family of music generation models. NeuralSpace offers the following models: Suno V5.5, Suno V5, Suno V4.5+, Suno V4.5, Suno V4. They all run through a single public API, and there is a ready MCP server for AI agents. The key is issued on the API keys page. Below are the model capabilities, request examples and setup steps.

What Suno can do

Suno generates music from a text description, usually two tracks per generation. Versions V5.5, V5, V4.5+, V4.5 and V4 are available. There is a normal description mode and a custom mode with lyrics, style and title. Generation is asynchronous: poll the status via GET /v1/music/generations/:id.

API endpoint

Send a request to POST /v1/music/generations. Example: {"model": "V5_5", "prompt": "a calm instrumental melody for background", "instrumental": true}. Authorization uses an API key in the x-api-key header. Available model ids: V5_5, V5, V4_5PLUS, V4_5, V4.

MCP tools

The NeuralSpace MCP server is available at POST /mcp (Streamable HTTP). To work with Suno, an agent uses the tools: generate_music, check_music, list_models, get_balance. This lets Claude Code, Cursor and other MCP clients use the site models directly.

How to connect

Sign up on NeuralSpace, open the API keys page and create an nsk-… key. Then pass it in the request header or in your MCP client settings. Full documentation is on the the /v1/docs page.

FAQ

How many tracks come per generation?

Usually two tracks per generation.

Can I provide song lyrics?

Yes, in custom mode you pass lyrics, style and title.

What format is the request?

POST /v1/music/generations with model and prompt fields.