mcpbeat Sign in

VEO 3.1 MCP Server

local only

VEO 3.1 runs on your own machine — the client starts it, so there is no endpoint to ping. 186 installs a week from pypi. Last commit 19 Apr 2026.

4K video generation via Google VEO 3.1: text-to-video, image-to-video, video extension

Installs per day peak 50 · avg 26 · -13% w/w
a month agotoday
186
Installs / week
pypi · veo-mcp-server
3
Stars
0 open issues
19 Apr 2026
Last commit
from GitHub
MIT
License
Python

What the code does

We read the source, 2 d ago · rules 995398eba69f

In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

        full_path = os.path.join(self.out_dir, f"{filename}.{self.config.default_image_format}")

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Nothing serious here today

Today is the operative word: we check VEO 3.1 every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add veo-mcp-server -- uvx veo-mcp-server
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "veo-mcp-server": {
      "command": "uvx",
      "args": [
        "veo-mcp-server"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.veo-mcp-server]
command = "uvx"
args = ["veo-mcp-server"]
.cursor/mcp.json
{
  "mcpServers": {
    "veo-mcp-server": {
      "command": "uvx",
      "args": [
        "veo-mcp-server"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "veo-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "veo-mcp-server"
      ]
    }
  }
}

Alternatives to VEO 3.1

same job, measured the same way
gflow-cli
by ffroliva

Drive Google Flow from an agent: Veo video and Imagen image generation

5 415 installs/wk local only
Media Gen MCP
by strato-space

MCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation.

91 installs/wk local only
MCP Veo
by acedatacloud

MCP server for Google Veo AI video generation

980 installs/wk answering
Gemini Image
by jimothysnicket

Google Gemini image generation, editing, and local processing via MCP

476 installs/wk local only
NanoBanana Pro 2
by u2n4

4K AI image generation via NanoBanana Pro 2: Pro + Flash models, Google Search grounding

85 installs/wk local only
Google Image
by codechap

MCP server for Google Gemini image generation and editing

local only
Nano Banana
by mindstone

Nano Banana MCP server — Google Gemini image generation and editing via Model Context Protocol

173 installs/wk local only
MCP Nano Banana
by codefi

MCP server for Google Nano Banana (Gemini) image generation

111 installs/wk local only

VEO 3.1 — questions

Answers built from our own checks of this server.

Why is there no uptime for VEO 3.1?
VEO 3.1 runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package veo-mcp-server was installed 186 times last week.
How do I connect VEO 3.1?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls veo-mcp-server straight from pypi; nothing to host, nothing to sign up for.
How many people use VEO 3.1?
The pypi package veo-mcp-server was installed 186 times in the last week. Week over week that is -13%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is VEO 3.1 open source?
Yes — it is published under the MIT licence, written in Python and 3 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.