nano-banana-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FLOW_CDP_URL | No | Endpoint de depuración del Chrome | http://127.0.0.1:9222 |
| FLOW_MAX_COST | No | Techo de puntos por generación | 0 |
| FLOW_OUTPUT_DIR | No | Dónde se guardan las imágenes | ~/nano-banana-images |
| FLOW_GENERATE_TIMEOUT_MS | No | Cuánto esperar la respuesta de Flow | 180000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| flow_statusA | Check the connection to the Google Flow Chrome window: signed-in session, account, open project and credit balance. Call this first when something fails. |
| generate_imageB | Generate one or more images with Google Flow and save them to disk. You can ask for an exact pixel size (e.g. 1200x630): it generates at the closest native aspect ratio and crops to the size you asked for. Images cost no credits. |
| download_imageA | Download an image that already exists in Flow by its media id, with optional cropping to an exact size. |
| list_libraryA | List the images in the Flow project library: uploads (reusable via reference_library_names without re-uploading) and generated images (re-downloadable by id with download_image). |
| generate_batchA | Generate several DIFFERENT prompts at once, one browser tab per prompt, in parallel. Much faster than calling generate_image repeatedly. Up to 4 jobs; each can have its own size and filename. Reference images are not supported here — use generate_image for that. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool maps to a distinct stage of the workflow: status, single generation, batch generation, listing, and downloading. generate_image and generate_batch overlap somewhat, but their descriptions clearly separate single/reference-image generation from parallel multi-prompt jobs.
Most tools follow a clear verb_noun pattern: generate_image, list_library, download_image, generate_batch. flow_status is a minor deviation since it is noun-like rather than an explicit action verb like check_flow_status or get_flow_status.
Five tools is well-scoped for a focused image-generation server. Each tool serves a necessary purpose without redundancy, and the count is within the ideal range.
The core workflow is covered: check status, generate images, generate batches, list library contents, and download images. Minor gaps exist such as no explicit upload, delete, or job-status tools, but those may be outside the server's intended scope.