MCP server · Generative art

Gemini Media MCP server

Lets your AI make images, videos, voice clips and music through Google's Gemini and Veo models.

Generative art Generative video Text to speech For creatives For marketing Multimedia Process

This is a small helper program that connects your AI assistant to Google's media-making models. Once it is set up, you can ask your AI in plain words to create a picture, a short video, a spoken audio clip or a piece of music, and it will do the work for you. It is handy for anyone who needs quick visuals, voiceovers or background music without learning a design or video tool.

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 service. This one connects your AI to Google's Gemini and Vertex AI media models, so it can actually make images, videos, speech and music when you ask. You talk to your AI like normal, and the helper quietly does the media work behind the scenes.

What this MCP server does

You type a request in your chat, like asking for a picture of a fox in the snow. Your AI passes that request to this helper program, which sends it to Google's Gemini or Vertex AI service. Google's models create the image, video, audio or music and send it back. The helper saves the finished file to a folder on your computer and tells your AI where it is, so you can open it. For videos, which take longer, you get a job number first and can check back until it is ready.

Flow diagram: you ask your AI “Make an image of a fox in the snow”, the Gemini Media MCP server works in steps: send your request, then create the media, then save the file, and you get back your finished file.

Click to zoom

What you can do with it

Create an image from a written description
Edit an existing image by describing the change you want
Combine up to three reference images into one new picture
Turn a written scene into a short video clip
Animate a still image into a moving video
Generate spoken audio from text with a chosen voice and language
Create a short music clip or a full song from a description

Try asking your AI

“Make a 16:9 image of a cozy reading nook with warm afternoon light”
“Turn this photo into a video where the clouds slowly drift by”
“Read this paragraph out loud in a calm female voice”
“Create a 30 second lo-fi hip-hop track with soft piano and vinyl crackle”

What it gives back to you

For images, audio and music you get a saved file on your computer plus a short note in the chat telling you where it is. For videos, you first get a job number, then you can ask your AI to check progress and download the finished clip when it is done. The chat also shows you details like the model used and the file path, so you can find and open what was made.

Before you start

What you need

A Google Gemini API key (a kind of password for apps; you get one from Google's AI studio) or a Google Cloud project set up for Vertex AI
The gemini-media-mcp program installed on your computer
An MCP client that can run it, such as the Claude desktop app or Claude Code
A folder where you want the generated files saved (optional, it defaults to one)

Good to know

Making media costs money on your Google account, and video especially adds up fast since it is billed per second, so check the prices before you generate a lot.

Install it with your AI

Add Gemini Media MCP server 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 Gemini Media MCP server, 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.