mcp-draw

mcp-draw

3.3

If you are the rightful owner of mcp-draw and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

MCP Draw is a server that utilizes the Model Context Protocol to generate images from text prompts using OpenAI's services.

MCP Draw

An MCP (Model Context Protocol) server for generating images from text prompts. This server allows AI assistants to create images / draw through a standardized interface.

📖 Resources

Prerequisites

  • Node.js (v18 or higher)
  • An OpenAI API key

Setup

1. API Key

First, get an OpenAI API key from OpenAI's platform. This will be used to authenticate the MCP server with OpenAI's services.

2. Configure MCP Client for Local Development

{
  "mcpServers": {
    "mcp-draw": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-draw@latest"
        "--api-key",
        "<REPLACE-WITH-YOUR-OPENAI-API-KEY>",
        "--output-dir",
        "/ABSOLUTE/PATH/TO/SAVE/OUTPUT_FOLDER"
      ]
    }
  }
}

Local Development Setup

1. API Key

First, get an OpenAI API key from OpenAI's platform. This will be used to authenticate the MCP server with OpenAI's services.

2. Clone the Repository

git clone https://github.com/kdr/mcp-draw.git
cd mcp-draw

3. Install Dependencies & Build the Server

npm install
npm run build

4. Configure MCP Client for Local Development

{
  "mcpServers": {
    "mcp-draw": {
      "command": "node",
      "args": [
        "/ABSOLUTE/PATH/TO/mcp-draw/build/index.js",
        "--api-key",
        "<REPLACE-WITH-YOUR-OPENAI-API-KEY>",
        "--output-dir",
        "/ABSOLUTE/PATH/TO/SAVE/OUTPUT_FOLDER"
      ]
    }
  }
}

Tools

The following tools are available to the LLM:

  • generate_image_from_description: Creates an image from a text prompt using OpenAI's gpt-image-1 model