Integration

OpenAI Sora integration

OpenAI's text-to-video generation model for creating realistic videos from text descriptions. Generate high-quality video content with natural motion, scene understanding, and creative storytelling. Designed for filmmaking, content creation, and applications requiring AI-generated video. DEPRECATED: The Sora 2 Videos API (sora-2, sora-2-pro and all dated snapshots) was deprecated on March 24, 2026 and shuts down on September 24, 2026.

Connect OpenAI Sora How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in OpenAI Sora.Built from the 8 OpenAI Sora tools below, on the connection you add once.

Common OpenAI Sora use cases

Free storage quota
Display user video generation history
Save generated video to local storage
Monitor long-running video generations
Create narrative videos for storytelling
Lengthen short clips for longer narratives
Modify lighting or atmosphere of existing videos
Generate multiple creative variants from one generation
Remove unused generations
Stream video to end users

What you can do with OpenAI Sora

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

create_videoCreate videoPOSTCreate a video generation job from a text prompt using OpenAI Sora. Returns immediately with status 'queued'; poll retrieve_video until status is 'completed'.
delete_videoDelete videoDELETEPermanently delete a Sora video job and all its stored assets.
download_video_contentDownload video contentGETDownload the raw video file for a completed Sora generation job. Returns binary video content.
edit_videoEdit videoPOSTEdit an existing completed Sora video with a new prompt to produce a modified version.
extend_videoExtend videoPOSTExtend an existing Sora video by appending newly generated seconds directed by an updated prompt.
list_videosList videosGETList all Sora video generation jobs for the current project with cursor-based pagination.
remix_videoRemix videoPOSTRemix a completed Sora video with a new prompt, producing a variant that preserves the original motion and scene structure.
retrieve_videoRetrieve videoGETRetrieve the current status and metadata of a Sora video generation job. Poll until status is 'completed' before calling download_video_content.

Use OpenAI Sora from Claude Code, Cursor or Codex

Connect OpenAI Sora in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its OpenAI Sora operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect OpenAI Sora

Create your workspace
Sign up free. Nothing to install.
Connect OpenAI Sora once
Add your OpenAI Sora connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

OpenAI Sora integration FAQ

What can you do with the OpenAI Sora integration?

LiveContext exposes 8 operations on OpenAI Sora, covering video. Common uses include Free storage quota, Display user video generation history and Save generated video to local storage.