Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Scenetra MCP make a 5-second product ad video: remove the background, then animate with Seedance"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Let Claude, Cursor and other AI agents build and run AI image and video workflows on Scenetra.
Your agent gets 60+ models (Kling, Seedance, Wan, PixVerse, Grok Imagine, FLUX, Nano Banana, GPT-Image, Seedream and more) on a visual node-based board. Every generation runs a live price auction across 16 providers and bills at provider cost with 0% markup, so the agent always gets the lowest price.
"Take this product photo, remove the background, and make a 5-second ad video with Seedance."
The agent builds the board, runs it, and hands you the outputs plus a link to the board, which you can open and keep editing.
Tool | What it does |
| How to build good boards (prompt reuse, wiring, layout). Agents call this first. |
| The available image, video and audio models, with prices. |
| A model's input fields and connection handles. |
| Build a board as a blueprint, without running it. Free. |
| Build and run a board. Returns a |
| Poll a run until it completes; returns the output URLs. |
| Add new steps to an existing board, optionally running them. |
Model ids are always routed to the cheapest provider that supports your settings.
Related MCP server: NexusBridge MCP Server
Sign up at app.scenetra.com (100 free credits, no card required).
Open Settings → MCP (app.scenetra.com/mcp) and create a token. It starts with sct_.
claude mcp add scenetra --transport http https://app.scenetra.com/api/mcp \
--header "Authorization: Bearer sct_YOUR_TOKEN"Add to mcpServers in Cursor's MCP settings:
{
"mcpServers": {
"scenetra": {
"url": "https://app.scenetra.com/api/mcp",
"headers": { "Authorization": "Bearer sct_YOUR_TOKEN" }
}
}
}Add to claude_desktop_config.json (or your client's MCP config):
{
"mcpServers": {
"scenetra": {
"command": "npx",
"args": ["-y", "scenetra-mcp"],
"env": { "SCENETRA_API_TOKEN": "sct_YOUR_TOKEN" }
}
}
}Add to .vscode/mcp.json:
{
"servers": {
"scenetra": {
"type": "http",
"url": "https://app.scenetra.com/api/mcp",
"headers": { "Authorization": "Bearer sct_YOUR_TOKEN" }
}
}
}The Scenetra MCP server is hosted at https://app.scenetra.com/api/mcp (Streamable HTTP). Clients that support remote servers connect to it directly.
This package, scenetra-mcp, is a small stdio bridge for clients that only launch local servers. It forwards every request to the hosted server with your token. Tools, models and pricing all live server-side, so you never need to update the bridge to get new models.
Environment variables:
Variable | Required | Default |
| yes | |
| no |
|
create_board is free. execute_board and extend_board with execute: true spend credits from your Scenetra account, at provider cost. list_models and get_model_schema show each model's price, and the agent gets an error with the amount needed if your balance is too low. Plans and credit packs: scenetra.com/pricing.
See examples/ for prompts that work well.
npm install
npm run build
SCENETRA_API_TOKEN=sct_... npx @modelcontextprotocol/inspector node dist/index.jsMIT
This server cannot be deployed
Build and run visual creative-production workflows from your AI agent.
Image, video, audio and chat from 61 AI models through one connector. Pay per use, no subscription.
Image, video, music and text generation across 100+ models through one endpoint.
run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
