Image Generation (Replicate) MCP server

Integrates with Replicate's API to generate images using Stable Diffusion XL, providing endpoints for creating and checking image generation predictions with authentication and CORS support.
Back to servers
Setup instructions
Provider
rmcendarfer2017
Release date
Mar 06, 2025
Language
TypeScript

The Image Generator MCP Server leverages Replicate to create and store images through a user-friendly interface. It provides tools to generate images with various style options, save them locally, and manage your generated image collection.

Installation

Prerequisites

Before using the Image Generator MCP Server, ensure you have:

  1. A Replicate account and API token
  2. Python installed on your system

Setup

  1. Clone the repository:

    git clone https://github.com/yourusername/image-generator.git
    cd image-generator
    
  2. Create and activate a virtual environment:

    # Using venv
    python -m venv .venv
    
    # On Windows
    .venv\Scripts\activate
    
    # On macOS/Linux
    source .venv/bin/activate
    
  3. Install dependencies:

    pip install -r requirements.txt
    
  4. Configure your Replicate API token:

Configuration

Claude Desktop Integration

On MacOS

Edit the configuration file at: ~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows

Edit the configuration file at: %APPDATA%/Claude/claude_desktop_config.json

Add the following to your configuration:

For development/unpublished servers:

"mcpServers": {
  "image-generator": {
    "command": "uv",
    "args": [
      "--directory",
      "path/to/image-generator",
      "run",
      "image-generator"
    ]
  }
}

For published servers:

"mcpServers": {
  "image-generator": {
    "command": "uvx",
    "args": [
      "image-generator"
    ]
  }
}

Usage

Generating Images

Use the generate-image tool with the following parameters:

  • prompt (required): Description of the image you want to create
  • negative_prompt (optional): Elements to exclude from the image
  • width (optional): Image width in pixels
  • height (optional): Image height in pixels
  • num_inference_steps (optional): Number of denoising steps
  • guidance_scale (optional): How closely the model follows your prompt

Example:

Generate an image of a futuristic city with flying cars

You can specify styles by adding style preferences:

  • Realistic: For photorealistic images
  • Artistic: For creative, stylized renderings
  • Abstract: For non-representational art

Saving Images

After generating an image, use the save-image tool to store it locally:

Required parameters:

  • image_url: URL of the generated image
  • prompt: The prompt used to generate the image

The image will be saved in the "generated_images" directory with metadata.

Viewing Saved Images

Use the list-saved-images tool to view all your saved images. The tool returns:

  • A list of all saved images
  • Their associated metadata
  • Thumbnail previews

You can also access individual images using the custom image:// URI scheme.

Resource System

The server implements a custom resource system where:

  • Each image has a unique URI using the image:// scheme
  • Images are named based on their prompts
  • All resources include creation dates and appropriate MIME types (image/png)

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "image-generator" '{"command":"uvx","args":["image-generator"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "image-generator": {
            "command": "uvx",
            "args": [
                "image-generator"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

{
    "mcpServers": {
        "image-generator": {
            "command": "uvx",
            "args": [
                "image-generator"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later