Flux ImageGen MCP Server
An MCP server for generating images using the Pollinations AI API.
Flux ImageGen MCP Server
A specialized Model Context Protocol (MCP) server for image generation and manipulation, powered by Pollinations AI.
Developer
- Author: Falah.G.Salieh
- Copyright: Ā© 2025 All rights reserved
Overview
ImageGen MCP Server is a streamlined server implementation that provides powerful image generation capabilities through the Model Context Protocol (MCP). This server specializes in three core functionalities:
- Image URL Generation
- Direct Image Generation
- Model Listing and Management
Features
- š¼ļø Image Generation: Create stunning images from text prompts
- šØ Multiple Models: Support for various image generation models
- š§ Flexible Configuration: Easy to set up and customize
- š High Performance: Optimized for quick response times
- š MCP Compatible: Fully compliant with Model Context Protocol
Installation
# Clone the repository
git clone https://github.com/yourusername/flux-imagegen-mcp-server.git
# Install dependencies
npm install
Configuration
Claude Desktop Configuration
To use this server with Claude Desktop, update your configuration file at:
C:\Users\[YourUsername]\AppData\Roaming\Claude\claude_desktop_config.json
{
"mcpServers": {
"mcpollinations": {
"command": "cmd",
"args": [
"/c",
"node",
"PATH_TO_YOUR_SERVER\\server.js"
],
"tools": [
"generateImageUrl",
"generateImage",
"listImageModels"
]
}
}
}
Replace PATH_TO_YOUR_SERVER with your actual server path.
Available Tools
1. Generate Image URL (generateImageUrl)
Generates a URL for an image based on a text prompt.
{
"prompt": "A beautiful sunset over mountains",
"model": "flux", // optional, defaults to 'flux'
"width": 1024, // optional
"height": 1024, // optional
"enhance": true, // optional
"safe": false // optional
}
2. Generate Image (generateImage)
Generates and saves an image directly from a text prompt.
{
"prompt": "A serene lake reflecting mountains",
"model": "flux",
"width": 1024,
"height": 1024,
"enhance": true,
"safe": false,
"outputPath": "./output",
"fileName": "mountain_lake",
"format": "png"
}
3. List Image Models (listImageModels)
Returns a list of available image generation models.
// Example response:
{
"models": [
{
"id": "flux",
"name": "Flux",
"description": "Default image generation model"
},
// ... other models
]
}
Running the Server
# Start the server
node server.js
Environment Requirements
- Node.js >= 16.0.0
- NPM >= 7.0.0
- Windows/Linux/MacOS compatible
Development
To contribute or modify the server:
- Fork the repository
- Create your feature branch
- Make your changes
- Submit a pull request
Error Handling
The server provides detailed error messages for common issues:
{
"error": {
"code": "ERROR_CODE",
"message": "Human-readable error message",
"details": { /* Additional error details */ }
}
}
Examples
Basic Image Generation
// Generate an image URL
const response = await generateImageUrl({
prompt: "A futuristic city at night",
model: "flux",
width: 1024,
height: 1024
});
// Generate and save an image
const image = await generateImage({
prompt: "A peaceful garden with butterflies",
outputPath: "./images",
fileName: "garden_scene"
});
Download Image Example
// Download an image from URL
const downloadResult = await downloadImage({
imageUrl: "https://example.com/image.jpg",
fileName: "downloaded-image",
format: "png"
});
Support
For issues and feature requests, please create an issue in the repository or contact the developer:
- Email: [Your contact email]
- GitHub: [Your GitHub profile]
License
This project is licensed under the MIT License - see the LICENSE file for details.
Made with ā¤ļø by Falah.G.Salieh Ā© 2025 All rights reserved
Related Servers
Pollinations MCP Server
Generate images and text using the Pollinations.ai API.
EdgeOne Pages MCP
An MCP server and client implementation for EdgeOne Pages Functions, supporting OpenAI-formatted requests.
vHAL MCP Server
Search Android Vehicle Hardware Abstraction Layer (vHAL) documentation and source code from a local repository clone.
Proteus Workflow Engine
A modern, extensible multi-agent workflow engine with real-time monitoring and a web visualization interface.
OpenRouter MCP Client for Cursor
An MCP client for Cursor that uses OpenRouter.ai to access multiple AI models. Requires an OpenRouter API key.
MCP Java Decompiler Server
Decompile Java class files from file paths, package names, or JAR files using a JavaScript port of the CFR decompiler.
Tecton
Feature engineering assistance using the Tecton platform, integrated with Cursor.
Dify Plugin Agent
An agent that supports Function Calling and ReAct for the MCP protocol via HTTP with SSE or Streamable HTTP transport.
E2B
Run code in secure sandboxes hosted by E2B
Chromium Helper
Access Chromium and PDFium source code repositories using Google's official CodeSearch APIs, supporting advanced search, Gerrit integration, and issue tracking.