Discover the AI Image Generation MCP server for creating images from text prompts with full MCP compliance and customizable parameters.

Sorry, the content could not found
An MCP (Model Context Protocol) server implementation for generating images using Replicate's black-forest-labs/flux-schnell model.
Ideally to be used with Cursor's MCP feature, but can be used with any MCP client.
Clone the repository
Install dependencies:
npm installAdd your Replicate API token directly in the code at src/imageService.ts by updating the apiToken constant:
// No environment variables are used since they can't be easily set in cursor
const apiToken = "your-replicate-api-token-here";Note: If using with Claude, you can create a
.envfile in the root directory and set your API token there:
REPLICATE_API_TOKEN=your-replicate-api-token-hereThen build the project:
npm run buildTo use with cursor:
node ./path/to/dist/server.js| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | - | Text prompt for image generation |
output_dir | string | Yes | - | Server directory path to save generated images |
go_fast | boolean | No | false | Enable faster generation mode |
megapixels | string | No | "1" | Resolution quality ("1", "2", "4") |
num_outputs | number | No | 1 | Number of images to generate (1-4) |
aspect_ratio | string | No | "1:1" | Aspect ratio ("1:1", "4:3", "16:9") |
output_format | string | No | "webp" | Image format ("webp", "png", "jpeg") |
output_quality | number | No | 80 | Compression quality (1-100) |
num_inference_steps | number | No | 4 | Number of denoising steps (4-20) |
{
"prompt": "black forest gateau cake spelling out 'FLUX SCHNELL'",
"output_dir": "/var/output/images",
"filename": "black_forest_cake",
"output_format": "webp"
"go_fast": true,
"megapixels": "1",
"num_outputs": 2,
"aspect_ratio": "1:1"
}{
"image_paths": [
"/var/output/images/output_0.webp",
"/var/output/images/output_1.webp"
],
"metadata": {
"model": "black-forest-labs/flux-schnell",
"inference_time_ms": 2847
}
}The server handles the following error types:
Each error response includes:
ISC