Ideogram MCP Server provides an interface to generate images using the Ideogram API (v3.0) through the Model Context Protocol. This TypeScript tool makes it easy to connect with Claude Desktop or other MCP clients for seamless image generation with features like style reference, magic prompts, aspect ratio controls, and model selection.
To quickly integrate with Claude Desktop or other MCP clients, copy the following JSON snippet to your configuration file:
{
"mcpServers": {
"ideogram": {
"command": "npx",
"args": [
"@sunwood-ai-labs/ideagram-mcp-server"
],
"env": {
"IDEOGRAM_API_KEY": "your_api_key_here"
}
}
}
}
Make sure to replace your_api_key_here with your actual Ideogram API key.
You can also install the package directly:
npm install @sunwood-ai-labs/ideagram-mcp-server
The main functionality of this server is provided through the generate_image tool.
| Parameter | Type | Description | Required | Notes |
|---|---|---|---|---|
| prompt | string | Image generation prompt (English recommended) | Required | |
| aspect_ratio | string | Aspect ratio (e.g., "1x1", "16x9", "4x3") | Optional | 15 types available |
| resolution | string | Resolution (see official docs for all 69 options) | Optional | |
| seed | integer | Random seed for reproducibility | Optional | 0-2147483647 |
| magic_prompt | string | Magic prompt ("AUTO", "ON", or "OFF") | Optional | Default: "AUTO" |
| rendering_speed | string | v3 rendering speed ("TURBO", "DEFAULT", "QUALITY") | Optional | |
| style_codes | string[] | Array of 8-character style codes | Optional | |
| style_type | string | Style type ("AUTO", "GENERAL", "REALISTIC", "DESIGN") | Optional | |
| negative_prompt | string | Elements to exclude (English recommended) | Optional | |
| num_images | number | Number of images to generate (1-8) | Optional | |
| style_reference | object | Style reference (Ideogram 3.0 feature) | Optional | See details below |
| └ urls | string[] | Array of reference image URLs (max 3) | Optional | |
| └ style_code | string | Style code | Optional | |
| └ random_style | boolean | Use random style | Optional | |
| output_dir | string | Image save directory | Optional | Default: "docs" |
| base_filename | string | Base filename for saved images | Optional | Default: "ideogram-image" |
| blur_mask | boolean | Blur image edges (true for mask composition) | Optional | Default: false |
Here's an example of how to use the MCP tool:
const result = await use_mcp_tool({
server_name: "ideagram-mcp-server",
tool_name: "generate_image",
arguments: {
prompt: "A beautiful sunset over mountains",
aspect_ratio: "16x9",
rendering_speed: "QUALITY",
num_images: 2,
style_reference: {
urls: [
"https://example.com/ref1.jpg",
"https://example.com/ref2.jpg"
],
random_style: false
},
blur_mask: true
}
});
The style reference feature allows you to provide reference images to guide the style of generated images:
style_reference: {
urls: ["https://example.com/reference1.jpg", "https://example.com/reference2.jpg"],
style_code: "ab12cd34", // Optional style code
random_style: true // Enable random style selection
}
The rendering_speed parameter affects quality and generation time:
"TURBO": Fastest generation but lower quality"DEFAULT": Balanced speed and quality"QUALITY": Highest quality but slower generationIf you encounter issues:
For persistent issues, you may need to check the server logs or refer to the Ideogram API documentation for limitations and requirements.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "ideogram" '{"command":"npx","args":["@sunwood-ai-labs/ideagram-mcp-server"],"env":{"IDEOGRAM_API_KEY":"your_api_key_here"}}'See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"ideogram": {
"command": "npx",
"args": [
"@sunwood-ai-labs/ideagram-mcp-server"
],
"env": {
"IDEOGRAM_API_KEY": "your_api_key_here"
}
}
}
}To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json2. Add this to your configuration file:
{
"mcpServers": {
"ideogram": {
"command": "npx",
"args": [
"@sunwood-ai-labs/ideagram-mcp-server"
],
"env": {
"IDEOGRAM_API_KEY": "your_api_key_here"
}
}
}
}3. Restart Claude Desktop for the changes to take effect