Getting Started
Scenario MCP gives AI agents — Claude, Cursor, VS Code, or any MCP-compatible client — full access to the Scenario creative AI platform. 19 tools covering image, video, 3D, and audio generation across 500+ models (+ your own), with an intelligence layer that handles model selection, parameter discovery, and prompt enhancement automatically.
Prerequisites
- A Scenario account — sign up at app.scenario.com
- API credentials (for API key auth) — app.scenario.com/team
- An MCP-compatible client (Claude Code, Cursor, VS Code, Windsurf, Claude Desktop, and more)
Installation
Connect the Scenario MCP server to your preferred AI coding tool. OAuth is the recommended method — it handles authentication automatically on first use.
Claude Code
claude mcp add --transport http scenario https://mcp.scenario.com/mcpOAuth authentication triggers automatically. Authenticate manually via /mcp if needed.
Cursor
Cursor 1.0+ supports native OAuth and Streamable HTTP. Open Settings → MCP and add:
{
"mcpServers": {
"scenario": {
"url": "https://mcp.scenario.com/mcp"
}
}
}OAuth triggers on first use.
VS Code
Press Cmd+P, type MCP: Add Server, select HTTP, and enter the URL. Or add to your settings:
{
"mcpServers": {
"scenario": {
"type": "http",
"url": "https://mcp.scenario.com/mcp"
}
}
}Activate via MCP: List Servers if not auto-enabled.
Windsurf
Open Settings → Cascade → MCP Servers → Add Server and add:
{
"mcpServers": {
"scenario": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.scenario.com/mcp"
]
}
}
}Requires Node.js. mcp-remote is installed automatically via npx.
Claude Desktop
Open Settings → Developer → MCP Servers and add:
{
"mcpServers": {
"scenario": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.scenario.com/mcp"
]
}
}
}Requires Node.js. mcp-remote is installed automatically via npx.
Codex
codex mcp add scenario -- npx -y mcp-remote@latest https://mcp.scenario.com/mcpOAuth triggers on first use.
Amp
amp mcp add scenario https://mcp.scenario.com/mcpOAuth authentication via Dynamic Client Registration.
Gemini CLI
Edit ~/.gemini/settings.json:
{
"mcpServers": {
"scenario": {
"url": "https://mcp.scenario.com/mcp"
}
}
}Run /mcp auth scenario to authenticate.
OpenCode
Edit ~/.config/opencode/opencode.json:
{
"mcp": {
"scenario": {
"type": "remote",
"url": "https://mcp.scenario.com/mcp",
"oauth": {}
}
}
}Run opencode mcp auth scenario to authenticate.
Warp
Open Settings → AI → Manage MCP servers → + Add → CLI Server. Enter this command:
npx -y mcp-remote@latest https://mcp.scenario.com/mcpOAuth triggers on first use.
Zed
Open settings (Cmd+,) and add:
{
"context_servers": {
"scenario": {
"command": {
"path": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://mcp.scenario.com/mcp"
]
}
}
}
}Other Clients
Any MCP client that supports OAuth and Streamable HTTP can connect directly to:
https://mcp.scenario.com/mcpFor clients that only support stdio, use npx mcp-remote@latest https://mcp.scenario.com/mcp as a bridge.
Using an API Key
If you prefer API key authentication instead of OAuth:
- Get your API key and secret from app.scenario.com
- Base64-encode your credentials:
echo -n 'KEY:SECRET' | base64 - Add the
Authorizationheader to your config
Claude Code
claude mcp add --transport http scenario \
https://mcp.scenario.com/mcp \
--header "Authorization: Basic $(echo -n 'KEY:SECRET' | base64)"JSON Config Clients (Cursor, VS Code, Gemini CLI, OpenCode)
{
"mcpServers": {
"scenario": {
"url": "https://mcp.scenario.com/mcp",
"headers": {
"Authorization": "Basic <YOUR_BASE64_ENCODED_KEY:SECRET>"
}
}
}
}mcp-remote Clients (Claude Desktop, Windsurf, Warp, Zed)
{
"mcpServers": {
"scenario": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.scenario.com/mcp",
"--header",
"Authorization: Basic <YOUR_BASE64_ENCODED_KEY:SECRET>"
]
}
}
}Test the Connection
Try these prompts to verify everything works:
- "List my Scenario teams"
- "Show available models for image generation"
- "Generate an image of a sunset over mountains"
Having trouble? See troubleshooting.
First Steps
Once connected, try these prompts in your AI Agent:
"Generate a pixel art knight with a red cape""What's the best model for YouTube thumbnails?""Show me my recent assets"