Skip to main content
Glama
runapi-ai

Nano Banana MCP Server

by runapi-ai

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RUNAPI_API_KEYNoYour RunAPI API key. Can also be set via config file at ~/.config/runapi/config.json

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

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
loginA

Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.

edit_imageC

Create a Nano Banana task on RunAPI (edit image). Returns a task id, status, and output URLs.

text_to_imageC

Create a Nano Banana task on RunAPI (text to image). Returns a task id, status, and output URLs.

get_taskA

Fetch the current status and latest result payload for a nano-banana task.

check_pricingB

Look up RunAPI pricing for the nano-banana model line.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: auth (login), pricing lookup (check_pricing), two creation paths split by modality (edit_image vs text_to_image), and polling (get_task). No two tools overlap—edit_image and text_to_image are cleanly separated by whether an input image is involved, while get_task handles result retrieval.

Naming Consistency4/5

Consistent snake_case verb_noun convention (check_pricing, edit_image, text_to_image, get_task). The lone exception is 'login', a bare verb with no object, though it stays in snake_case and is unambiguous.

Tool Count5/5

Five tools is well-scoped for a single model-line integration: authentication, pricing, two generation modes, and result polling. Each tool earns its place with no redundancy or filler.

Completeness4/5

Covers the core lifecycle—authenticate, check cost, submit edit/text-to-image tasks, and poll results. Minor gaps exist: no list_tasks or cancel/delete task operation, and no explicit reference-image upload, but agents can work around these.

Maintenance

ActivityMaintained
ResponsivenessNo issues