Skip to main content
Glama
nanana-app

Nanana AI Image Generation Server

by nanana-app
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

@nanana-ai/mcp-server-nano-banana

MCP (Model Context Protocol) server for Nanana AI image generation service powered by Google Gemini's nano banana model. This server allows Claude Desktop and other MCP clients to generate and transform images using nano banana's powerful image generation capabilities.

Installation

npm install -g @nanana-ai/mcp-server-nano-banana

Related MCP server: Nano Banana MCP Server

Configuration

1. Get your API token

  1. Visit nanana.app and sign in

  2. Go to your account dashboard

  3. Generate an API token in the "API Access" section

  4. Copy and save the token (it will only be shown once)

2. Configure Claude Desktop

Add the server to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "nanana": {
      "command": "npx",
      "args": ["-y", "@nanana-ai/mcp-server-nano-banana"],
      "env": {
        "NANANA_API_TOKEN": "your-api-token-here"
      }
    }
  }
}

3. Restart Claude Desktop

After saving the config file, restart Claude Desktop to load the MCP server.

Available Tools

text_to_image

Generate an image from a text prompt.

Parameters:

  • prompt (string, required): The text description of the image to generate

Example:

Generate an image of a cute cat wearing a hat

image_to_image

Transform existing images based on a text prompt.

Parameters:

  • imageUrls (array of strings, required): 1-9 image URLs to transform

  • prompt (string, required): The text description of how to transform the images

Example:

Transform these images to look like oil paintings: ["https://example.com/image1.jpg"]

Environment Variables

  • NANANA_API_TOKEN (required): Your Nanana AI API token

  • NANANA_API_URL (optional): Custom API URL (defaults to https://nanana.app)

Development

Local Testing

  1. Clone the repository

  2. Install dependencies: npm install

  3. Build: npm run build

  4. Test locally by updating Claude Desktop config to point to the built file:

{
  "mcpServers": {
    "nanana": {
      "command": "node",
      "args": ["/path/to/packages/mcp-server/dist/index.js"],
      "env": {
        "NANANA_API_TOKEN": "your-token",
        "NANANA_API_URL": "http://localhost:3000"
      }
    }
  }
}

Build

npm run build

Watch mode

npm run dev

Credits and Pricing

Image generation with nano banana consumes credits from your Nanana AI account. Check your dashboard at nanana.app/account to view your credit balance and purchase more credits if needed.

Support

For issues and questions:

License

MIT

Available Tools

2 tools
image_to_imageA

Transform existing images based on a text prompt using Nanana AI. This operation typically takes 15-30 seconds to complete. The tool will wait for transformation to finish and return the final image URL.

ParametersJSON Schema
NameRequiredDescriptionDefault
imageUrlsYesArray of image URLs to transform (1-9 images)
promptYesThe text prompt describing how to transform the images

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: the operation takes 15-30 seconds, the tool waits for completion, and it returns a final image URL. This covers timing, blocking behavior, and output format - important information not available elsewhere.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with zero waste: first states purpose, second provides timing information, third describes blocking behavior and return value. Each sentence earns its place and the description is appropriately sized for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations and no output schema, the description does well by covering purpose, timing, blocking behavior, and return format. However, it doesn't mention potential errors, rate limits, or authentication requirements that might be relevant for an AI image transformation service.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description doesn't add any additional meaning about the parameters beyond what the schema provides (image URLs array with 1-9 items, text prompt). Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Transform existing images'), the resource ('images'), and the method ('based on a text prompt using Nanana AI'). It distinguishes from the sibling tool 'text_to_image' by specifying it works with existing images rather than generating from text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context about when to use this tool (transforming existing images with a text prompt) and implicitly distinguishes it from 'text_to_image' which likely generates images from text. However, it doesn't explicitly state when NOT to use this tool or mention specific alternatives beyond the sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

text_to_imageA

Generate an image from a text prompt using Nanana AI. This operation typically takes 15-30 seconds to complete. The tool will wait for generation to finish and return the final image URL.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesThe text prompt describing the image to generate

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It effectively describes key behavioral traits: the asynchronous nature of the operation (15-30 second completion time), the synchronous tool behavior (will wait for generation), and the return value (final image URL). This goes beyond what the input schema provides.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with three focused sentences: purpose statement, timing information, and behavioral details. Every sentence earns its place by providing essential information without redundancy or unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (asynchronous operation with waiting behavior), no annotations, and no output schema, the description provides good contextual coverage. It explains the operation timing, waiting behavior, and return format. However, it doesn't mention potential failure modes, rate limits, or authentication requirements that would be helpful for a complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents the single 'prompt' parameter. The description doesn't add any additional parameter semantics beyond what's in the schema. Baseline score of 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Generate an image'), identifies the resource ('from a text prompt'), and specifies the service provider ('using Nanana AI'). It distinguishes from the sibling tool 'image_to_image' by focusing on text-to-image generation rather than image-to-image transformation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context through the mention of generation time (15-30 seconds) and the tool's waiting behavior, but it doesn't explicitly state when to use this tool versus alternatives. No explicit guidance on when-not-to-use or comparison with the sibling tool 'image_to_image' is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • First observedimage_to_image
    • First observedtext_to_image
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: image_to_image transforms existing images based on text prompts, while text_to_image generates new images from text prompts. There is no overlap or ambiguity between these operations.

Naming Consistency5/5

Both tools follow a perfect verb_noun pattern (image_to_image, text_to_image) with consistent snake_case formatting. The naming convention is predictable and readable throughout the set.

Tool Count2/5

With only 2 tools for an AI image generation server, the surface feels thin and incomplete. While the two core operations are covered, typical image generation servers would include additional functionality like parameter controls, style options, batch operations, or image editing capabilities.

Completeness2/5

The server covers the basic text-to-image and image-to-image transformations but lacks essential functionality for a complete image generation workflow. There are no tools for controlling generation parameters (like resolution, style, seed values), managing generated images, editing existing images beyond transformations, or handling batch operations.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches