Gemini Image Studio runs on your own machine — the client starts it, so there is no endpoint to ping. 50 installs a week from npm. Last commit 4 Apr 2026.
AI image generation and editing with Google Gemini. Structured JSON editing.
Today is the operative word: we check Gemini Image Studio every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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.
claude mcp add gemini-image-studio -- npx -y gemini-image-studio-mcp
{
"mcpServers": {
"gemini-image-studio": {
"args": [
"-y",
"gemini-image-studio-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.gemini-image-studio]
command = "npx"
args = ["-y", "gemini-image-studio-mcp"]
{
"mcpServers": {
"gemini-image-studio": {
"args": [
"-y",
"gemini-image-studio-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"gemini-image-studio": {
"args": [
"-y",
"gemini-image-studio-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
GEMINI_API_KEY (Google AI Studio API key for Gemini).
The author declared them in the registry entry; get the values from the project itself.
MCP server for Google Gemini image generation and editing
Google Gemini image generation, editing, and local processing via MCP
Generate and edit images with Google Gemini (Nano Banana / Nano Banana Pro) image models.
Nano Banana MCP server — Google Gemini image generation and editing via Model Context Protocol
MCP server for Google Nano Banana (Gemini) image generation
MCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation.
Drive Google Flow from an agent: Veo video and Imagen image generation
MCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX)
Answers built from our own checks of this server.