Try “Veo”, “voiceover”, “thumbnail” or “Descript” · Esc to close

MCP Servers for Google Cloud Genmedia 🔌 MCP server Freemium

Google Cloud sample servers for Veo, Gemini Image, Gemini TTS, Lyria and AV compositing

Media generation MCP servers · Freemium ★ 1.2k · Apache-2.0 · updated 2026-09-25

6.9editor score
View on GitHub ↗
GitHub stars
1.2k
Stars this week
–
Forks
375
Licence
Apache-2.0
Last push
2026-09-25
Maintainer
Google Cloud Platform
Installcurl -sL https://raw.githubusercontent.com/GoogleCloudPlatform/genmedia-creative-studio/main/experiments/mcp-genmedia/mcp-genmedia-go/install-online.sh | bash

Third-party MCP servers run with your permissions and API keys. Read the source before installing, and prefer pinned versions.

Works with

Built on the open MCP client standard, so it works in every app that supports MCP client.

Good for

About MCP Servers for Google Cloud Genmedia

What it is

MCP Servers for Google Cloud Genmedia is a set of Go-based MCP servers published in Google Cloud's Creative Studio repository. Each server wraps a Vertex AI generative media API, so an agent can make video with Veo, images with Gemini Image models, speech with Gemini TTS and Chirp 3 HD, and music with Lyria, then combine them with an audio/video tool.

Key features

  • Veo 3 and 3.1 video generation
  • Gemini Image (3.1 Flash, 3 Pro, 2.5 Flash variants)
  • Gemini TTS and Chirp 3 HD speech
  • Lyria music generation
  • AVTool for compositing audio and video (built on FFmpeg)
  • Pre-compiled binaries for macOS, Linux and Windows

How to install

Run the install script from the README (curl -sL .../install-online.sh | bash), which detects your OS and downloads the binaries. Authenticate with gcloud auth application-default login or a service-account key in GOOGLE_APPLICATION_CREDENTIALS, and point the servers at a Google Cloud project with Vertex AI enabled. The README shows setups for Gemini CLI, Google ADK, Firebase Genkit and MCP Inspector; other MCP clients use the same stdio binaries.

Pricing and rights

The code is Apache-2.0 and free. Every call is billed to your Google Cloud project at Vertex AI rates, with no subscription. Google's generative media outputs carry SynthID watermarks per Google's model docs; check Vertex AI terms for commercial use.

Who it is for

Developers and studios on Google Cloud who want Veo, Lyria and Google speech in one agent pipeline.

Verdict

Covers Google's full media stack with a useful compositing tool. The repo says it is not an officially supported Google product, and the Google Cloud setup is heavy for solo creators.

veo lyria google-cloud video-generation text-to-speech

Pros

  • Veo, Gemini Image, TTS and Lyria in one set
  • AVTool for compositing
  • Apache-2.0, prebuilt binaries

Cons

  • Marked as not an officially supported Google product
  • Requires a Google Cloud project and billing
  • Docs target Gemini CLI and ADK more than other clients

fal MCP 🔌 MCP serverFreemium

Hosted fal.ai server to search, price and run 1,000+ image, video and audio models

8.2 Visit ↗

Comfy MCP 🔌 MCP serverOpen source

Comfy Org's official MCP for local ComfyUI and Comfy Cloud workflows

★ 234

7.9 Visit ↗

HeyGen MCP 🔌 MCP serverFreemium

Hosted HeyGen server for avatar videos, video translation and templates from any agent

7.8 Visit ↗

Replicate MCP 🔌 MCP serverFreemium

Official Replicate server to search and run thousands of open models from a chat

7.8 Visit ↗

Runway MCP 🔌 MCP serverFreemium

Hosted Runway server to generate images and video with your Runway plan credits

7.8 Visit ↗

Popular searches