Home / AI video generation

ONE MCP CONNECTION · VIDEO

AI video generation with an MCP connector

Turn a description or a first frame into a short video. Keep the creative brief in your assistant and follow the job until the finished clip is available.

What you can do

  • Create a video from a description or an image used as the first frame.
  • Use reference media where the selected model supports it.
  • Check an unfinished job with video_status; status checks are free.
  • Current HeyGen settings include 5–15 seconds, 480p or 768p, and supported landscape, square and portrait ratios.

Try this brief

Example prompt · not a claim that this output has already been generated

Make a 5-second, 16:9 video of sunlight moving across a quiet coffee shop table. Gentle camera movement, natural atmosphere, 480p.

Available tools: video_generate / video_status

Models and pricing

Current enabled models · usage-based credits
ModelStarting rate
HeyGen Video 1heygen-video-13 credits / second

1 credit ≈ US$0.01. Settings and reference inputs can affect the final quote. Current account pricing takes precedence.

Before you start

A video job can take longer than one tool call. A first frame and reference media are alternative input modes. Reference-video pricing may multiply the billable duration; check the account quote before creating.

Connect with remote MCP over Streamable HTTP and OAuth. Google sign-in creates your Lavis account. Interactive previews require MCP Apps support; download files you want to keep before their 7-day expiry.

Keep creating