Seedance API and MCP: how to add video generation to your project

Seedance is a video generation model. NeuralSpace offers the following models: Seedance 2.0. 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 Seedance can do

Seedance 2.0 generates video from a text description. Generation is asynchronous: POST creates a task and returns an id, then you poll the status via GET /v1/videos/generations/:id until it is ready. Fast or standard speed and 720p or 1080p resolution are available, priced per second.

API endpoint

Send a request to POST /v1/videos/generations. Example: {"model": "seedance-2.0", "prompt": "close-up of a product on a dark table", "duration": 5, "resolution": "720p"}. Authorization uses an API key in the x-api-key header. Available model ids: seedance-2.0.

MCP tools

The NeuralSpace MCP server is available at POST /mcp (Streamable HTTP). To work with Seedance, an agent uses the tools: generate_video, check_video, 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

Is generation synchronous or asynchronous?

Asynchronous: POST creates a task, then poll the status via GET /v1/videos/generations/:id.

Which resolutions are available?

720p and 1080p, with fast or standard speed.

What format is the request?

POST /v1/videos/generations with model, prompt, duration and resolution fields.