MCP server for AI image generation & editing with Google Gemini. Structured JSON editing for precise control. Powered by Nano Banana.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add gemini-image-studio --env GEMINI_API_KEY='<GEMINI_API_KEY>' -- npx -y gemini-image-studio-mcp~/.codex/config.toml
[mcp_servers.gemini-image-studio]
command = "npx"
args = ["-y", "gemini-image-studio-mcp"]
env = { GEMINI_API_KEY = "<GEMINI_API_KEY>" }
# codex mcp add gemini-image-studio --env GEMINI_API_KEY='<GEMINI_API_KEY>' -- npx -y gemini-image-studio-mcp~/.cursor/mcp.json
{
"mcpServers": {
"gemini-image-studio": {
"command": "npx",
"args": [
"-y",
"gemini-image-studio-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"gemini-image-studio": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"gemini-image-studio-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"gemini-image-studio": {
"command": "npx",
"args": [
"-y",
"gemini-image-studio-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"gemini-image-studio": {
"command": "npx",
"args": [
"-y",
"gemini-image-studio-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"gemini-image-studio": {
"command": "npx",
"args": [
"-y",
"gemini-image-studio-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}Environment variables
GEMINI_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.