Server facts
nano-banana-mcp
Project
- Author
- ConechoAI
- Repository
- github.com/ConechoAI/Nano-Banana-MCP
- License
- Not specified
- Category
- Design & Creative
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 234
- Last commit
- Data as of
Tags
- ai image generation
- google s gemini 2 5 flash image api
- mcp
- nano banana
Overview
Image creation and revision in Nano-Banana use Google’s Gemini 2.5 Flash Image API, with separate tools for starting a picture and changing existing work. The generate_image tool turns a description into new output, while edit_image targets an image identified by its file path. For subsequent revisions, continue_editing works from the session’s most recent result without requiring that path again. Both editing tools accept optional reference images for visual guidance, supporting workflows that move from an initial concept through style changes and further adjustments.
The get_last_image_info tool reports details such as the current image’s location and size, helping users identify what they can revise next. Credential setup is handled through configure_gemini_token, and get_configuration_status checks whether a token has been configured. The project also supports supplying credentials through MCP client configuration or the system environment. Images are saved automatically, with storage locations adapted for Windows, macOS, and Linux. Documented client workflows include Claude Code and Cursor, where users can request application visuals, mockups, prototypes, and other project assets.
nano-banana-mcp setup notes
- nano-banana-mcp records stdio only; confirm a network transport upstream before planning remote access.
- nano-banana-mcp has no recorded license; confirm reuse terms in its repository.