image-gen MCP Server

What is image-gen MCP Server?

A MCP server that provides text-to-image generation capabilities using the Stable Diffusion WebUI API (ForgeUI/AUTOMATIC-1111). It is designed for developers who want to integrate AI image generation into MCP-based applications.

How to use image-gen MCP Server?

Install Node.js and a Stable Diffusion WebUI instance running with the --api flag. Clone the repository, run npm install and npm run build, then add the server configuration to your MCP client, setting required environment variables such as SD_WEBUI_URL and SD_OUTPUT_DIR.

Key features of image-gen MCP Server

• Generate images from text prompts using Stable Diffusion.
• List and switch between available Stable Diffusion models.
• Retrieve available upscaler models.
• Upscale existing images with configurable settings.
• Supports negative prompts, seeds, batch generation, face restoration, and tiling.

Use cases of image-gen MCP Server

• Generating images for creative projects and prototypes.
• Integrating AI image generation into chatbots or automation workflows.
• Batch generating multiple image variations for design exploration.
• Upscaling low-resolution or generated images for higher quality.
• Using different Stable Diffusion models to achieve varied artistic styles.

FAQ from image-gen MCP Server

What are the prerequisites for running image-gen MCP Server?

You need Node.js and a running Stable Diffusion WebUI instance (ForgeUI or AUTOMATIC-1111) started with the --api flag enabled.

How do I configure authentication for the WebUI?

Optionally set the SD_AUTH_USER and SD_AUTH_PASS environment variables if your WebUI instance requires basic authentication.

What tools does image-gen MCP Server provide?

It provides five tools: generate_image, get_sd_models, set_sd_model, get_sd_upscalers, and upscale_images.

How do I set up the server from source?

Clone the repository, run npm install to install dependencies, then npm run build to compile the server. Add the configuration to your MCP client with the required environment variables.

What common errors might occur and how can I fix them?

Ensure the WebUI is running with --api, the URL is accessible, authentication credentials are correct if used, and the output directory exists with write permissions. For upscaling, verify input image files exist.