Together AI Image MCP Server
About
Enables the generation of images using Together AI's models through an MCP server, supporting customizable parameters such as model selection, image dimensions, and output directory.
Details
- Repository
- stefanskiasan/togetherai-image-mcp-server
- License
- MIT
Explore
- Supports Together AI's latest FLUX.1.1-pro model
- Automatically resizes images if dimensions are below 256 pixels
- Maintains aspect ratio during resizing
- High-quality JPEG output (90% quality)
- Creates output directories recursively
- Returns detailed metadata including image dimensions
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
Together AI Image MCP ServerCommand (node, npx, python, etc.)nodeArguments-
Argument 1
/path/to/togetherai-image-server/build/index.js
Environment-
TOGETHER_API_KEY
your-api-key-here
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
1. Install dependencies:
npm install
2. Build the server:
npm run build
Add the server to your Cline MCP settings file:
For macOS/Linux: ~/Library/Application Support/Windsurf/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
{
"mcpServers": {
"togetherai-image": {
"command": "node",
"args": ["/path/to/togetherai-image-server/build/index.js"],
"env": {
"TOGETHER_API_KEY": "your-api-key-here"
},
"disabled": false,
"autoApprove": []
}
}
}
The server provides a generate_image tool with the following parameters:
{
prompt: string; // Required: Text description of the image to generate
model?: string; // Optional: Model to use (default: 'black-forest-labs/FLUX.1.1-pro')
width?: number; // Optional: Image width in pixels (default: 1024)
height?: number; // Optional: Image height in pixels (default: 768)
steps?: number; // Optional: Number of inference steps (default: 28)
n?: number; // Optional: Number of images to generate (default: 1)
outputDir?: string; // Optional: Directory where images will be saved (default: './output')
}
You can use the server in Cline like this:
Generate an image of a cat and save it to my desktop:
<use_mcp_tool>
<server_name>togeherai-image</server_name>
<tool_name>generate_image</tool_name>
<arguments>
{
"prompt": "A cute cat sitting on a windowsill",
"outputDir": "/Users/username/Desktop/generated-images"
}
</arguments>
</use_mcp_tool>
generate_image
Generate an image based on a text description. Parameters: prompt (string, required), model (string, optional), width (number, optional), height (number, optional), steps (number, optional), n (number, optional), outputDir (string, optional)
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"together ai image mcp server": {
"env": {
"TOGETHER_API_KEY": "your-api-key-here"
},
"args": [
"/path/to/togetherai-image-server/build/index.js"
],
"command": "node"
}
}
}Linux
{
"env": {
"TOGETHER_API_KEY": "your-api-key-here"
},
"args": [
"/path/to/togetherai-image-server/build/index.js"
],
"command": "node"
}Macos
{
"env": {
"TOGETHER_API_KEY": "your-api-key-here"
},
"args": [
"/path/to/togetherai-image-server/build/index.js"
],
"command": "node"
}Windows
{
"env": {
"TOGETHER_API_KEY": "your-api-key-here"
},
"args": [
"/path/to/togetherai-image-server/build/index.js"
],
"command": "node"
}An MCP server for generating images using Together AI's image generation models.
<a href="https://glama.ai/mcp/servers/2cwphjnpgw"></a>
Setup
1. Install dependencies:
npm install
2. Build the server:
npm run build
Configuration
1. Together AI API Key
The server requires a Together AI API key. You can get one from Together AI's platform.
2. Cline Configuration
Add the server to your Cline MCP settings file:
For macOS/Linux: ~/Library/Application Support/Windsurf/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
{
"mcpServers": {
"togetherai-image": {
"command": "node",
"args": ["/path/to/togetherai-image-server/build/index.js"],
"env": {
"TOGETHER_API_KEY": "your-api-key-here"
},
"disabled": false,
"autoApprove": []
}
}
}
Usage in Cline
The server provides a generate_image tool with the following parameters:
{
prompt: string; // Required: Text description of the image to generate
model?: string; // Optional: Model to use (default: 'black-forest-labs/FLUX.1.1-pro')
width?: number; // Optional: Image width in pixels (default: 1024)
height?: number; // Optional: Image height in pixels (default: 768)
steps?: number; // Optional: Number of inference steps (default: 28)
n?: number; // Optional: Number of images to generate (default: 1)
outputDir?: string; // Optional: Directory where images will be saved (default: './output')
}
Example Usage
You can use the server in Cline like this:
Generate an image of a cat and save it to my desktop:
<use_mcp_tool>
<server_name>togeherai-image</server_name>
<tool_name>generate_image</tool_name>
<arguments>
{
"prompt": "A cute cat sitting on a windowsill",
"outputDir": "/Users/username/Desktop/generated-images"
}
</arguments>
</use_mcp_tool>
Output
The tool returns a JSON response containing:
- filepath: Full path to the saved image
- filename: Name of the saved image file
- dimensions: Original and final dimensions of the image
Features
- Supports Together AI's latest FLUX.1.1-pro model
- Automatically resizes images if dimensions are below 256 pixels
- Maintains aspect ratio during resizing
- High-quality JPEG output (90% quality)
- Creates output directories recursively
- Returns detailed metadata including image dimensions
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
