Image Generation MCP Server

Model Context Protocol (MCP) server enabling AI clients (Cline, Claude Desktop) to generate images using OpenAI (DALL-E 3, gpt-image-1) and save them

Remote serverstreamable-httpTypeScript

What is the Image Generation MCP Server?

Model Context Protocol (MCP) server enabling AI clients (Cline, Claude Desktop) to generate images using OpenAI (DALL-E 3, gpt-image-1) and save them directly to

What the server does

This is a Model Context Protocol (MCP) server that allows compatible clients (like Cline, Claude Desktop, etc.) to generate images using OpenAI's API (gpt-image-1, dall-e-3, dall-e-2).

  • Generates images from text prompts using OpenAI models (gpt-image-1, dall-e-3, dall-e-2)
  • Edits and combines existing images using reference images with OpenAI's gpt-image-1 model
  • Supports optional branding guidelines via a brandSignature parameter
  • Allows specifying image size, quality, and background type (transparent or opaque)
  • Supports consistent visual styling through the styleDefinitionJSON parameter
  • Saves generated images to a target project directory specified by the LLM client

Credentials and setup notes

  1. Node.js: Version 18 or higher recommended. 2. npm: Comes with Node.js. 3. OpenAI API Key: You need an API key from OpenAI. Visit platform.openai.com/api-keys to create one. Note that usage of gpt-image-1 might require API Organization Verification.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Configuration

  1. Node.js: Version 18 or higher recommended. 2. npm: Comes with Node.js. 3. OpenAI API Key: You need an API key from OpenAI. Visit platform.openai.com/api-keys to create one. Note that usage of gpt-image-1 might require API Organization Verification.
VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes

Frequently asked questions

The server supports `gpt-image-1`, `dall-e-3`, and `dall-e-2`. Image editing operations automatically use `gpt-image-1`.