Nano Banana Mcp

io.github.runapi-builderPublished by GitHub account runapi-builderv0.2.1Updated Oct 29, 2026

RunAPI MCP server for Nano Banana: create tasks, poll status, check pricing.

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

RunAPI's Nano Banana MCP server lets an assistant create image generation and image editing tasks, poll their status, and check model pricing.

What you can do
  • Create image tasks: submit Nano Banana text-to-image or edit-image jobs, optionally waiting for a terminal status
  • Check task results: fetch current status and latest output payload for an existing task by ID
  • Check pricing: look up RunAPI pricing for Nano Banana models and endpoints, even before signing in
  • Authenticate: run a browser login flow that saves the RunAPI API key to the shared config file
When to use it
Use it when an assistant should generate or edit images through RunAPI's Nano Banana models and stay scoped to that model line, rather than loading the full RunAPI catalog. Useful for hosts that need task IDs and output URLs returned for later polling.
Requirements
Runs locally over stdio via npx from the npm package, so Node.js is needed. Task creation and polling require a RunAPI account: either the login tool (browser flow writing to the RunAPI config file) or the RUNAPI_API_KEY environment variable for headless and CI hosts. Pricing lookup works without a key. Network access to RunAPI is required.
Before you install
Task creation spends money on RunAPI, so confirm cost before expensive or batch requests. The login tool writes an API key to a shared config file; keep that file and any RUNAPI_API_KEY out of version control. Image prompts and inputs are sent to RunAPI's service.

Installation

In SourceWeft

  1. Open Nano Banana Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

RunAPI Nano Banana MCP Server

Nano Banana API access for AI agents: run image generation operations, poll asynchronous results, and check pricing through one focused MCP server.

Works with Claude Code, Codex, Cursor, Windsurf, VS Code, Roo Code, and any MCP-compatible host.

[npm version] [GitHub repository] [Apache-2.0 license] [MCP Server] [5 models]

Install | Tools | Models | Agent Prompts | Configuration | Links


Why This Package?

@runapi.ai/nano-banana-mcp is a focused Model Context Protocol server for the Nano Banana model line on RunAPI. It gives MCP-compatible assistants direct access to 2 endpoints and 5 model variants without loading the full RunAPI catalog.

Use this per-model server when an agent should stay scoped to Nano Banana. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.


Install

Add it to Claude Code:

bash
claude mcp add nano-banana -s user -- npx -y @runapi.ai/nano-banana-mcp

Use project scope when the server should be shared with a repository:

bash
claude mcp add nano-banana -s project -- npx -y @runapi.ai/nano-banana-mcp

Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:

json
{  "mcpServers": {    "nano-banana": {      "command": "npx",      "args": ["-y", "@runapi.ai/nano-banana-mcp"]    }  }}

check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login. Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.

Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.


Tools

ToolAuthPurpose
edit_imageYesCreate a Nano Banana edit image task and optionally wait for a terminal status. Returns the task id, status, and output URLs.
text_to_imageYesCreate a Nano Banana text to image task and optionally wait for a terminal status. Returns the task id, status, and output URLs.
get_taskYesFetch the current status and latest payload for an existing task.
check_pricingNoLook up current pricing for a Nano Banana model and endpoint.

Models

Nano Banana covers 5 model variants across 2 endpoints. Each tool accepts the models listed for it:

ToolModels
edit_imagenano-banana-2-lite, nano-banana-edit
text_to_imagenano-banana, nano-banana-2, nano-banana-2-lite, nano-banana-pro

Model availability can change between releases. Use check_pricing or the Nano Banana model page for the current catalog view.


Agent Prompts

Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.

Create a task

text
Run a Nano Banana edit image task with RunAPI.

The assistant can call check_pricing, then edit_image, and return the task id, status, and output URLs.

Submit without waiting

text
Create the task but don't wait for it to finish.

The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.

Check pricing before creating

text
Check current Nano Banana pricing, then create the task if it matches my request.

The assistant calls check_pricing and can link to the Nano Banana model page for the canonical catalog entry.


Configuration

The server resolves auth in this order:

  1. RUNAPI_API_KEY environment variable, useful for headless and CI hosts
  2. ~/.config/runapi/config.json, created by the MCP login tool or runapi login
  3. No key, which still allows check_pricing

The config file is normally managed by login. A pre-provisioned headless config can use:

json
{  "apiKey": "your_runapi_key"}

Do not commit real API keys.


Links

ResourceURL
Nano Banana model pagehttps://runapi.ai/models/nano-banana
npm package@runapi.ai/nano-banana-mcp
GitHub repositoryrunapi-ai/nano-banana-mcp
RunAPI MCP overviewrunapi.ai/mcp
RunAPI docsrunapi.ai/docs

License

Licensed under the Apache License, Version 2.0.

Source: README.md at commit 7d7b639

Tools

5

login

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

Parametersforce

edit_image

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

Parameterswaitmodelprompttimeout_msaspect_ratiocallback_urloutput_formatpoll_interval_mssource_image_urlsrequired

text_to_image

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

Parameterswaitmodelprompttimeout_msaspect_ratiocallback_urloutput_formatpoll_interval_msoutput_resolutionreference_image_urls

get_task

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

Parametersactionrequiredtask_idrequired

check_pricing

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

Parametersmodelaction

Version history

3
  1. v0.2.1LatestOct 22, 2026
  2. v0.2.0Sep 30, 2026
  3. v0.1.12Sep 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts