Integration

Velora MCP Server

Connect Claude Desktop and other AI assistants directly to the Velora Video Engine. Give your AI the power to autonomously generate videos.

🔌 What is MCP?

The Model Context Protocol (MCP) is an open standard that allows AI models to interact with external tools and data. By installing the Velora MCP Server, you give your AI assistant direct control over our video generation pipeline.

Once installed, you can simply tell Claude: "Generate a cinematic YouTube short about Ancient Rome." Claude will automatically write the script, call our API to render the video, and return the final MP4 link directly in your chat.

⚙️ Installation & Supported Clients

The Velora MCP server works with any MCP-compatible AI assistant. Because Velora MCP handles authentication dynamically via tool arguments, you do not need to set any API key environment variables in your config file. Your AI assistant will prompt you for your API key during the conversation!

Claude Desktop

Add the Velora server to your Claude config file:

Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

"mcpServers": {
  "velora": {
    "command": "npx",
    "args": ["-y", "velora-mcp-server@latest"]
  }
}

CCursor IDE

Cursor natively supports MCP servers to allow its AI composer to generate videos directly in your IDE.

Open Cursor Settings (Ctrl/Cmd + Shift + J).
Navigate to Features > MCP.
Click + Add New MCP Server.
Name: velora
Type: command
Command: npx -y velora-mcp-server@latest

WWindsurf IDE

Windsurf supports MCP servers via its global configuration file.

Edit your Windsurf MCP config:

Mac: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

"mcpServers": {
  "velora": {
    "command": "npx",
    "args": ["-y", "velora-mcp-server@latest"]
  }
}

🛠️ Available Tools

create_video
Triggers a new AI video generation. Supports parameters for language, AI voiceover, aspect ratio, background music, video style, and visual model (e.g. Veo, Sora, Kling).
check_video_status
Polls the generation status of a currently rendering video to see if it is pending, processing, or completed.
get_video_result
Retrieves the final MP4 download link, generated script, thumbnails, and metadata for a completed video.
estimate_video_cost
Calculates the compute credit cost for a video configuration before rendering it.

Ready to upgrade your agent?

Get your API key to start generating videos programmatically.

Get API Key