labnana-mcp

An MCP server for the Labnana OpenAPI. It enables Claude, Claude Code, and other MCP clients to generate and edit images with Labnana.

Supported model families include:

• Gemini image models (Nano Banana Pro / 2)

• GPT-Image-2

• Wan2.7 Image / Pro

• Seedream 5.0 Pro, including precise editing

GitHub · npm · 中文文档

Installation

Claude Code

1. Create an API key in the Labnana API Keys console.

2. Make LABNANA_API_KEY available in the environment used by Claude Code.

3. Add the server:

claude mcp add labnana -- npx -y @exoticknight/labnana-mcp@1.0.0

The package can also be started directly with:

npx -y @exoticknight/labnana-mcp@1.0.0

Claude Desktop and other MCP clients

Use an equivalent mcpServers configuration:

{
  "mcpServers": {
    "labnana": {
      "command": "npx",
      "args": ["-y", "@exoticknight/labnana-mcp@1.0.0"],
      "env": {
        "LABNANA_API_KEY": "lh_xxxxxxxxx"
      }
    }
  }
}

Local source checkout

npm install
npm run build

Then configure the server with the generated dist/index.js:

claude mcp add labnana -- node <path-to-repo>/dist/index.js

On Windows, use an absolute path such as:

claude mcp add labnana -- node C:/path/to/labnana-mcp/dist/index.js

Related MCP server: nano-banana-claude

Configuration

The server reads the following environment variable:

The command-line options below are also supported:

Environment variables are recommended because command-line arguments may be visible in the local process list.

Tools

Usage

Synchronous generation

{
  "name": "generate_image",
  "arguments": {
    "provider": "google",
    "model": "gemini-3-pro-image",
    "prompt": "Change the background of the image to the grasslands of Inner Mongolia",
    "referenceImages": [
      {
        "fileData": {
          "fileUri": "https://cdn.labnana.com/xxx.png",
          "mimeType": "image/png"
        }
      }
    ],
    "imageConfig": {
      "imageSize": "2K",
      "aspectRatio": "16:9"
    }
  }
}

Use referenceImages for image-to-image generation and editing. fileData.fileUri supports gs:// and https://; small images can be passed as base64 through inlineData.data.

Asynchronous generation

For large images or batch jobs, use:

generate_image_async -> wait_for_generation_task

The completed task returns a public image URL.

Credit estimation

{
  "name": "estimate_credits",
  "arguments": {
    "provider": "google",
    "prompt": "A Shiba Inu running through a snowy landscape",
    "imageConfig": {
      "imageSize": "4K"
    }
  }
}

Parameters

• provider: google, openai, alibaba, or bytedance; routing follows model.

• model (default: gemini-3-pro-image): gemini-3-pro-image, gemini-3.1-flash-image, gpt-image-2, wan2.7-image-pro, wan2.7-image, or seedream-5-0-pro.

• imageConfig.imageSize: 1K, 2K, or 4K. wan2.7-image does not support 4K; seedream-5-0-pro supports only 1K and 2K.

• imageConfig.aspectRatio: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, or 8:1. GPT-Image-2 may omit this field and let the service choose; Wan2.7 supports only 1:1, 16:9, 9:16, 4:3, and 3:4.

• referenceImages: up to 14 for Gemini, 4 for GPT-Image-2, 9 for Wan2.7, and 10 for Seedream.

Credit summary

Errors

API errors are returned as { code, message } and exposed as MCP results with isError: true.

Development

npm install
npm run typecheck
npm test

Links

• Labnana integration guide

• Labnana OpenAPI reference

• Credit guide

• GitHub repository

• Technical support: support@marswave.ai

License

Apache-2.0