Nano Banana MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 29 installs a week from npm.
AI image generation and editing with Google Gemini: Nano Banana 2.1, Pro and Lite models
Today is the operative word: we check Nano Banana MCP 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 nano-banana-mcp -- npx -y @fjacquet/nano-banana-mcp
{
"mcpServers": {
"nano-banana-mcp": {
"args": [
"-y",
"@fjacquet/nano-banana-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.nano-banana-mcp]
command = "npx"
args = ["-y", "@fjacquet/nano-banana-mcp"]
{
"mcpServers": {
"nano-banana-mcp": {
"args": [
"-y",
"@fjacquet/nano-banana-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"nano-banana-mcp": {
"args": [
"-y",
"@fjacquet/nano-banana-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
GEMINI_API_KEY (Gemini API key from Google AI Studio. Optional: it can also be set later with the configure_gemini_token tool.).
The author declared them in the registry entry; get the values from the project itself.
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
AI image generation and editing with Google Gemini. Structured JSON editing.
Google Gemini image generation, editing, and local processing via MCP
Generate images (Nano Banana), video (Veo, Gemini Omni), speech and music (Lyria) with Google models
4K AI image generation via NanoBanana Pro 2: Pro + Flash models, Google Search grounding
MCP server for Google Gemini image generation and editing
MCP server for Google Nano Banana (Gemini) image generation
Answers built from our own checks of this server.