Image Generation MCP Server

Image Generation MCP Server

What is Image Generation MCP Server about?

Image Generation MCP Server enables generation of images from textual prompts by leveraging the Flux model hosted on Replicate. It returns URLs to the created images in common formats.

How to use Image Generation MCP Server?

1. Installation – install via NPX (no local setup) or globally/local NPM package.
2. Configuration – add an MCP server entry to Claude Desktop config, specifying the command npx @gongrzhe/image-gen-server and setting environment variables:
   • REPLICATE_API_TOKEN (required)
   • MODEL (optional, defaults to black-forest-labs/flux-schnell)
3. Tool call – invoke the generate_image tool with arguments such as prompt, aspect_ratio, output_format, etc., through the use_mcp_tool API.

Key features of Image Generation MCP Server

• Direct integration with Replicate’s Flux model for high‑quality image synthesis.
• Supports custom model selection via the MODEL env variable.
• Configurable output format (webp, jpg, png) and aspect ratios.
• Ability to generate multiple images (1‑4) per request.
• Simple NPX‑based deployment, requiring only an API token.

Use cases of Image Generation MCP Server

• Rapid prototyping of visual concepts for designers.
• Generating illustrative assets for content creators.
• Providing on‑demand image creation in conversational AI applications.
• Automating batch image generation for marketing or UI mockups.

FAQ from the Image Generation MCP Server

Q: What API token is needed? A: A Replicate API token, obtainable from your Replicate account under API Tokens.

Q: Can I use a different model? A: Yes, set the MODEL environment variable to any compatible Replicate model name.

Q: How many images can be generated at once? A: Up to 4 images per request via the num_outputs parameter.

Q: Which image formats are supported? A: webp, jpg, and png (default is webp).

Q: Do I need to install anything locally? A: No, the NPX method runs the server directly from npm without local files.

Image Generation MCP Server

This MCP server provides image generation capabilities using the Replicate Flux model.

Installation

Installing via Smithery

To install Image Generation MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @GongRzhe/Image-Generation-MCP-Server --client claude

Option 1: NPX Method (No Local Setup Required)

You can use the package directly from npm without installing it locally:

# No installation needed - npx will handle it

Option 2: Local Installation

If you prefer a local installation:

# Global installation
npm install -g @gongrzhe/image-gen-server

# Or local installation
npm install @gongrzhe/image-gen-server

Setup

Configure Claude Desktop

Edit your Claude Desktop configuration file:

• On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• On Windows: %APPDATA%/Claude/claude_desktop_config.json

Option 1: NPX Configuration (Recommended)

This method runs the server directly from npm without needing local files:

{
  "mcpServers": {
    "image-gen": {
      "command": "npx",
      "args": ["@gongrzhe/image-gen-server"],
      "env": {
        "REPLICATE_API_TOKEN": "your-replicate-api-token",
        "MODEL": "alternative-model-name"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Option 2: Local Installation Configuration

If you installed the package locally:

{
  "mcpServers": {
    "image-gen": {
      "command": "node",
      "args": ["/path/to/image-gen-server/build/index.js"],
      "env": {
        "REPLICATE_API_TOKEN": "your-replicate-api-token",
        "MODEL": "alternative-model-name"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Get Your Replicate API Token

1. Sign up/login at https://replicate.com
2. Go to https://replicate.com/account/api-tokens
3. Create a new API token
4. Copy the token and replace your-replicate-api-token in the MCP settings

Environment Variables

• REPLICATE_API_TOKEN (required): Your Replicate API token for authentication
• MODEL (optional): The Replicate model to use for image generation. Defaults to "black-forest-labs/flux-schnell"

Configuration Parameters

• disabled: Controls whether the server is enabled (false) or disabled (true)
• autoApprove: Array of tool names that can be executed without user confirmation. Empty array means all tool calls require confirmation.

Available Tools

generate_image

Generates images using the Flux model based on text prompts.

Parameters

• prompt (required): Text description of the image to generate
• seed (optional): Random seed for reproducible generation
• aspect_ratio (optional): Image aspect ratio (default: "1:1")
• output_format (optional): Output format - "webp", "jpg", or "png" (default: "webp")
• num_outputs (optional): Number of images to generate (1-4, default: 1)

Example Usage

const result = await use_mcp_tool({
  server_name: "image-gen",
  tool_name: "generate_image",
  arguments: {
    prompt: "A beautiful sunset over mountains",
    aspect_ratio: "16:9",
    output_format: "png",
    num_outputs: 1
  }
});

The tool returns an array of URLs to the generated images.

📜 License

This project is licensed under the MIT License.