Image-Gen-Server MCP Server: Enhancing Text-to-Image Generation for AI Applications

Overview: What is Image-Gen-Server MCP Server?

The Image-Gen-Server MCP Server, built specifically for integration with Cursor IDE and powered by即梦AI (Aidream AI), transforms textual descriptions into visual images. Designed as a middleware to connect advanced AI applications like Claude Desktop and Continue, it bridges the gap between text-based prompts and image generation, offering robust features such as automatic image saving, custom save paths, and multiple output capabilities.

🔧 Core Features & MCP Capabilities

The Image-Gen-Server leverages Model Context Protocol (MCP) for seamless integration. It supports various AI applications through its versatile MCP client compatibility matrix, ensuring broad adoption across the ecosystem. Key functionalities include:

Seamless Integration with MCP Clients

• Claude Desktop: Fully supported.
• Continue: Fully supported.
• Cursor: Tool-only integration currently.

The server uses uv for running the MCP protocol and executes commands to generate images based on provided text prompts. This process involves setting up APIs, image generation, and handling responses efficiently.

Real-Time Image Generation

Upon receiving a prompt from an AI application, it triggers the generation of one or more images, which are then saved in configured directories. The server uses asynchronous programming for efficient processing and returns results promptly to the calling application.

The generate_image function, defined within server.py, encapsulates the logic for generating images based on detailed text prompts. This function takes parameters such as prompt, file name, sample strength, width, and height to produce high-quality outputs.

async def generate_image(prompt: str, file_name: str, save_folder: str = None, sample_strength: float = 0.5, width: int = 1024, height: int = 1024) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
    """Generate an image based on a text prompt

    Args:
        prompt: Text description of the desired image.
        file_name: Name of the generated image (excluding extension; defaults to .jpg).
        save_folder: Absolute path for saving images (default uses IMG_SAVA_FOLDER).
        sample_strength: Image generation quality parameter (0-1 range, default 0.5).
        width: Width resolution of the generated image (default 1024).
        height: Height resolution of the generated image (default 1024).

    Returns:
        List: Generated content including text and image resources.
    """

⚙️ MCP Architecture & Protocol Implementation

The core architecture of Image-Gen-Server is built around MCP, ensuring compatibility with various AI applications. It follows a client-server model where MCP clients (such as Cursor) initiate interactions by sending text prompts to the server.

Mermaid Diagram: Model Context Protocol Flow

graph TD
    A[AI Application] -->|MCP Client| B[MCP Protocol]
    B --> C[MCP Server]
    C --> D[Data Source/Tool]
    style A fill:#e1f5fe
    style C fill:#f3e5f5
    style D fill:#e8f5e8

Mermaid Diagram: Image Generation Data Architecture

graph TD
    M[Model Context] -->|MCP Protocol| S[MCP Server]
    S -> G[Graphics Server] -- API Call --> P[Parameterized Prompt]
    P -.-> I[Image Generation] -.-> O[Output Storage]
    O --> R[Result] --> S
    M --> S

🚀 Getting Started with Installation

To install Image-Gen-Server, follow these steps:

1. Prepare the Environment: Ensure you have Python 3.10+ and Node.js installed.

   • Check compatibility for specific versions (v20 recommended).

2. Install Dependencies:

   git clone https://github.com/fengin/image-gen-server.git
   cd image-gen-server
   pip install -r requirements.txt
   pip install uv
   npm i -g @modelcontextprotocol/[\[email protected\]](/cdn-cgi/l/email-protection)
   

3. Set API Token and Default Image Path: Modify server.py to include your JIMENG_API_TOKEN and IMG_SAVA_FOLDER.

💡 Key Use Cases in AI Workflows

Workflow: Product Logo Creation

• Scenario:
  • A developer needs a product logo for their new project.
• Implementation:
  • The user provides the text prompt to Cursor, which then uses Image-Gen-Server to generate an image based on the provided description.

根据项目需求，帮我生成一张产品logo，放在项目目录images下面。

Workflow: Website Homepage Design

• Scenario:
  • A website designer wants to create a homepage with a banner.
• Implementation:
  • Using Cursor, the user can send detailed prompts to Image-Gen-Server for generating various design elements and placeholders.

根据项目需求，帮我制作网站的首页，头部需要有banner图片。

🔌 Integration with MCP Clients

Configuration Steps in Cursor

1. Open Cursor Settings:

   • Click the settings icon at the bottom left.
   • Navigate to Features > MCP Servers.
   • Add "Add new MCP server".

2. Fill in Server Details:

   • Name: image-gen-server (or any preferred name).
   • Type: command.
   • Command:

     uv run --with fastmcp fastmcp run D:\code\image-gen-service\server.py
     

3. Black Window Issue: Ensure the command path is correctly configured, and use a compatible terminal.

📊 Performance & Compatibility Matrix

MCP Client	Resources	Tools	Prompts
Claude Desktop	✅	✅	✅
Continue	✅	✅	✅
Cursor	❌	✅	❌

🛠️ Advanced Configuration & Security

For debugging and advanced configurations:

• Replace the command with dev mode for detailed logs.
• Use MCP Inspector to debug server operations.

Debugging Example

uv run --with fastmcp fastmcp dev D:/code/image-gen-service/server.py

❓ Frequently Asked Questions (FAQ)

1. How do I get the JIMENG_API_TOKEN?
   • Visit https://jimeng.jianying.com/, log in, and find your token.
2. Why does Cursor not provide direct support for text inputs?
   • Cursor is currently tool-only integration with additional setup required.
3. Can I customize the image generation parameters?
   • Yes, via generate_image function settings like sample strength and resolution.
4. How do I update the server configuration remotely?
   • Use API calls or external tools to modify configurations programmatically.
5. What are common issues when integrating with MCP clients?
   • Ensure correct environment setup and command paths.

🌐 MCP Ecosystem & Resources

Stay updated by exploring the Model Context Protocol documentation and community forums for future updates and integrations. Image-Gen-Server provides a powerful foundation for developers aiming to bridge text-based prompts with advanced image generation, enhancing AI application workflows through comprehensive MCP integration.

This document aims to provide a detailed understanding of the Image-Gen-Server's capabilities and serves as a guide for developers looking to implement similar solutions in their AI applications.