MCP server · Generative video
Google Flow MCP server (gflow-cli)
by ffroliva
Make videos and images with Google Flow's Veo and Imagen models straight from your AI chat.
This is a helper that connects your AI assistant to Google Flow, Google's tool for making videos and images with AI. Once it is set up, you can ask your AI to create a video or a picture and it will run the job in Flow using your own Google account. It is handy if you already have Flow access and want to make clips or images without clicking around the Flow website yourself.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another app or service. This one connects your AI to Google Flow, so when you ask for a video or an image, the AI can actually go and make it in your Flow account. You stay in the chat, and the helper does the clicking behind the scenes.
What this MCP server does
You type a request in plain words, like making a short video of a forest at sunrise. Your AI passes that request to this helper. The helper opens a real Chrome window on your computer and drives Google Flow the same way a person would, using your logged-in Google account. Flow makes the video or image, and the helper saves the file and tells your AI it is done. Your AI then shows you the result in the chat.
Click to zoomWhat you can do with it
- Create a video from a text description
- Turn a still image into a short video clip
- Make an image from a text description
- Extend an existing video clip past its normal length
- Create a reusable character so the same person shows up again
- Rewrite a short prompt into a more detailed one before generating
- Run the same request over a list of prompts in a batch
Try asking your AI
- “Make a short video of a hot air balloon over Tokyo at sunrise”
- “Turn this photo into a video where the camera slowly pushes in”
- “Create an image of a cozy reading nook in soft morning light”
- “Extend my last video by a few more seconds”
What it gives back to you
You get back the finished file: a video clip or an image, saved on your computer or in the storage you set up. Your AI also tells you where the file landed and how the run went. If something goes wrong, you get a clear error instead of a silent failure. For images and simple edits, nothing is charged; only video generation uses your Flow credits.
Before you start
What you need
- A Google account with access to Google Flow
- Google Chrome installed on your computer
- Python and the gflow-cli tool installed (the README shows the exact commands)
- Flow credits in your Google account if you want to make videos
Good to know
This tool drives your own Google account through a real browser, so it can spend your Flow video credits and may go against Google's terms of service; images and simple edits are free, but video generation costs credits.
Install it with your AI
Add Google Flow MCP server (gflow-cli) to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Google Flow MCP server (gflow-cli), install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
People who already use Google Flow and want to make videos or images in batches or from their AI chat, like content creators, marketers, and small video teams.
