Sora2

Exposes tools to create, manage, and remix AI-generated videos via OpenAI's Sora API.

typescript

2

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "nanameru-sora2-mcp": {
      "command": "npx",
      "args": [
        "sora2-mcp"
      ],
      "env": {
        "SORA2_MCP_API_KEY": "sk-your-real-key"
      }
    }
  }
}

Sora2 MCP exposes tools to programmatically create, manage, and remix AI-generated videos using OpenAI's Sora API. It enables prompt-first workflows in MCP-compatible clients, so you can automate video generation, track progress, and retrieve final assets with ease.

How to use

You use Sora2 MCP by connecting an MCP client to the local or remote MCP server and invoking the available tools. The core workflow is to create a video job with a prompt describing your shot, monitor its status, and download the finished video, thumbnail, or spritesheet. You can also remix an existing completed video by applying a new prompt. Each operation returns a job object with an ID that you poll until it completes.

How to install

Prerequisites: install Node.js 18 or newer and prepare an OpenAI API key with Sora access.

Set your API key in the environment. For example:

export SORA2_MCP_API_KEY=sk-your-real-key

How to install

Install dependencies and build the server locally.

cd /path/to/sora2-mcp
npm i
npm run build

How to install

Run the MCP server locally using the standard runtime command shown for local setups.

npx sora2-mcp

Configuration and startup

Configure the environment variable for the server and, if desired, set a server name override.

SORA2_MCP_API_KEY=sk-your-real-key
MCP_NAME=sora2-mcp

Additional setup for clients

If you use integration clients like Claude Desktop, VS Code, or LM Studio, provide the MCP connection using the same command and API key. The examples show how to add or configure the MCP server in each client’s settings or CLI.

Troubleshooting

401 authentication errors indicate the API key is missing or invalid. Verify that SORA2_MCP_API_KEY (or OPENAI_API_KEY) is set and that your account has access to the Sora API.

Ensure you are running Node.js 18 or newer. Check the version with node -v.

Local runs: after building, test locally with npx sora2-mcp. If you encounter startup issues, confirm that the environment variables are exported in your shell or your client configuration.

Notes

Video generation times vary by model, resolution, and prompt complexity. Use polling or callbacks to monitor progress and retrieve results when status becomes completed.

Available tools

create_video

Start a new video generation job with Sora. Provide a prompt describing the desired shot, model, size, duration, and optional input reference to guide the initial frame.

get_video_status

Query the current status and progress of a video generation job by its ID.

download_video

Download the completed outputs for a video, including the MP4, thumbnail, or spritesheet, encoded in base64.

list_videos

List video jobs with pagination to support dashboards or housekeeping tasks.

delete_video

Permanently remove a video from storage by its ID.

remix_video

Create a new video by applying edits to an existing completed video, producing a new job.