Nano Banana MCP Server is a production-ready Model Context Protocol server that provides AI-powered image generation capabilities using Google's Gemini models with intelligent model selection.
From the registry: An MCP server that provides image generation and editing capabilities
Please install the `nanobanana-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **uv / uvx** — Install uv (Python package manager) (https://docs.astral.sh/uv/)
- **Google Gemini API key** — Get a free key from Google AI Studio (https://makersuite.google.com/app/apikey)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["nanobanana-mcp-server@latest"]
- required environment variables:
- `GEMINI_API_KEY`: Google Gemini API key (example: `<your-gemini-api-key>`)
- optional environment variables:
- `NANOBANANA_AUTH_METHOD`: Authentication method: api_key | vertex_ai | auto (example: `api_key`)
- `GCP_PROJECT_ID`: GCP project ID (only for vertex_ai auth) (example: `<your-gcp-project-id>`)
- `GCP_REGION`: GCP region (only for vertex_ai auth) (example: `us-central1`)
- `NANOBANANA_MODEL`: Model selection: flash | nb2 | pro | auto (example: `auto`)
- `IMAGE_OUTPUT_DIR`: Where to save generated images (example: `~/nanobanana-images`)
Note: AI image generation via Gemini 3.1 Flash Image (NB2) and Gemini 3 Pro Image. Supports aspect ratio control and Google Search grounding.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GEMINI_API_KEYrequiredAPI key for accessing Google Gemini services.NANOBANANA_AUTH_METHODrequiredAuthentication method for the server, can be set to 'api_key', 'vertex_ai', or 'auto'.GCP_PROJECT_IDrequiredGoogle Cloud project ID for Vertex AI authentication.GCP_REGIONGoogle Cloud region, default is 'us-central1'.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
MCP Toolbox for Databases enables your agent to connect to your database.
MCP Toolbox for Databases enables your agent to connect to your database.