Image Generator
About
Enables AI assistants to create images using Replicate or Together AI's image generation models through a flexible tool that accepts parameters like prompt, width, height, and can be run locally or deployed as a Docker container.
Details
- Author
- gmkr
- Repository
- GMKR/mcp-imagegen
- GitHub stars
- 3
- Categories
- Developer Tools, AI, Other, Productivity, Design, Media, Infrastructure, Frontend, API
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Image GeneratorCommand (node, npx, python, etc.)pnpxArguments-
Argument 1
-y -
Argument 2
tsx -
Argument 3
/path/to/mcp-imagegen/src/index.ts
Environment-
PROVIDER
replicate -
REPLICATE_API_TOKEN
your-replicate-api-token
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
The MCP Image Generator provides a tool called generate_image that can be used to generate images based on text prompts.
{
"mcpServers": {
"imagegenerator": {
"url": "http://localhost:3000/sse",
"env": {
"PROVIDER": "replicate",
"REPLICATE_API_TOKEN": "your-replicate-api-token"
}
}
}
}
Adjust the url to the endpoint of the MCP server you want to use. provider can be "replicate" or "together".
- PROVIDER: The provider to use for image generation (default: "replicate")
- REPLICATE_API_TOKEN: Your Replicate API token
- TOGETHER_API_KEY: Your Together AI API key
- MODEL_NAME: The model to use for image generation (default: "black-forest-labs/flux-schnell")
generate_image
Generates an image based on the provided prompt. Parameters: prompt (string), width (optional number, default: 512), height (optional number, default: 512), numberOfImages (optional number, default: 1)
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"image generator": {
"env": {
"PROVIDER": "replicate",
"REPLICATE_API_TOKEN": "your-replicate-api-token"
},
"args": [
"-y",
"tsx",
"/path/to/mcp-imagegen/src/index.ts"
],
"command": "pnpx"
}
}
}
Linux
{
"env": {
"PROVIDER": "replicate",
"REPLICATE_API_TOKEN": "your-replicate-api-token"
},
"args": [
"-y",
"tsx",
"/path/to/mcp-imagegen/src/index.ts"
],
"command": "pnpx"
}
Macos
{
"env": {
"PROVIDER": "replicate",
"REPLICATE_API_TOKEN": "your-replicate-api-token"
},
"args": [
"-y",
"tsx",
"/path/to/mcp-imagegen/src/index.ts"
],
"command": "pnpx"
}
Windows
{
"env": {
"PROVIDER": "replicate",
"REPLICATE_API_TOKEN": "your-replicate-api-token"
},
"args": [
"/c",
"pnpx",
"-y",
"tsx",
"/path/to/mcp-imagegen/src/index.ts"
],
"command": "cmd"
}
A Model Context Protocol (MCP) server for generating images using Together AI's image generation models. This MCP Server can be run locally or using an SSE endpoint. The MCP Image Generator required a provider, only "Replicate" and "Together" are supported currently. You need to set theTOGETHER_API_KEYorREPLICATE_API_TOKENenvironment variables. and set thePROVIDERenvironment variable to "replicate" or "together"/
git clone https://github.com/gmkr/mcp-imagegen.git cd mcp-imagegen
docker build -f Dockerfile.server -t mcp-imagegen . docker run -p 3000:3000 mcp-imagegen
{ "mcpServers": { "imagegenerator": { "url": "http://localhost:3000/sse", "env": { "PROVIDER": "replicate", "REPLICATE_API_TOKEN": "your-replicate-api-token" } } } }
Adjust theurlto the endpoint of the MCP server you want to use.providercan be "replicate" or "together".
- Node.js
- Together AI API key or Replicate API token
git clone https://github.com/gmkr/mcp-imagegen.git cd mcp-imagegen
Create a configuration file for your MCP client. Here's an example configuration:
{ "mcpServers": { "imagegenerator": { "command": "pnpx", "args": [ "-y", "tsx", "/path/to/mcp-imagegen/src/index.ts" ], "env": { "PROVIDER": "replicate", "REPLICATE_API_TOKEN": "your-replicate-api-token" } } } }
Replace/path/to/mcp-imagegenwith the absolute path to your cloned repository andyour-replicate-api-tokenwith your actual Replicate API token.
The MCP Image Generator provides a tool calledgenerate_imagethat can be used to generate images based on text prompts.
Generates an image based on the provided prompt.
- prompt(string): The text prompt to generate an image for
- width(number, optional): The width of the image to generate (default: 512)
- height(number, optional): The height of the image to generate (default: 512)
- numberOfImages(number, optional): The number of images to generate (default: 1)
- PROVIDER: The provider to use for image generation (default: "replicate")
- REPLICATE_API_TOKEN: Your Replicate API token
- TOGETHER_API_KEY: Your Together AI API key
- MODEL_NAME: The model to use for image generation (default: "black-forest-labs/flux-schnell")
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Generate images using Amazon Nova Canvas with text prompts and color guidance.
Server for advanced AI-driven video editing, semantic search, multilingual transcription, generative media, voice cloning, and content moderation.
Generate images using the Together AI API. Supports custom aspect ratios, save paths, and batch generation.
Trim, watermark, extract audio from, and convert any video to 9:16 vertical — via REST API or MCP tools for Claude, Cursor, and other AI agents.
Generate images using OpenAI's DALL-E API.
Generate images from text using Flux and Stable Diffusion models.
Integrates the Dify AI API to generate Ant Design business component code. Supports text, image inputs, and streaming responses.
A server for the Fal.ai text-to-image API, powered by OpenAI's image model. Requires Fal.ai and OpenAI API keys.
Advanced text-to-image generation using the fal.ai Recraft v3 API.
A frontier image generation and editing model with advanced text rendering and contextual understanding, powered by the FAL AI API.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





