Integration

Google Veo integration

Google Veo video generation via the Gemini API. Veo 3.1 generates high-fidelity 4-8 second videos (720p, 1080p or 4K) with natively generated audio, from a text prompt, from a reference image (image-to-video), from first/last frames, or by extending a previously generated Veo video. Generation is asynchronous: submit with generate_video, poll the returned operation with get_operation until done=true, then fetch the MP4 with download_video (the result is stored as a fileRef for downstream nodes). Generated videos are retained on Google's servers for 2 days.

Connect Google Veo How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Google Veo.Built from the 3 Google Veo tools below, on the connection you add once.

Common Google Veo use cases

Poll until done=true to obtain the video uri
Persist the generated video beyond Google's 2-day retention
Generate a cinematic clip with native audio from a text prompt
Animate a still image into a video (image-to-video)
Send the generated video to Telegram, email or storage
Detect safety-filtered generations via raiMediaFilteredCount
Display the video in an interface node
Produce vertical 9:16 clips for social media
Surface generation failures with error.message
Extend a previously generated Veo video with new footage

What you can do with Google Veo

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.

Video, 2 operations

download_videoDownload videoGETDownload the finished Veo video as binary MP4 and store it as a fileRef.
generate_videoGenerate videoPOSTStart an asynchronous Veo video generation job from a text prompt and optional image/frames. Returns an operation name to poll with get_operation.

Video operation, 1 operation

get_operationGet operationGETPoll a Veo video generation operation until done=true, then read the generated video uri.

Use Google Veo from Claude Code, Cursor or Codex

Connect Google Veo in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Google Veo 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 Google Veo

Create your workspace
Sign up free. Nothing to install.
Connect Google Veo once
Add your Google Veo 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.

Google Veo integration FAQ

What can you do with the Google Veo integration?

LiveContext exposes 3 operations on Google Veo, covering video and video operation. Common uses include Poll until done=true to obtain the video uri, Persist the generated video beyond Google's 2-day retention and Generate a cinematic clip with native audio from a text prompt.