Replicate Flux MCP is a server that enables AI assistants to generate high-quality images and vector graphics using advanced AI models. It connects to Replicate's API to access the Flux Schnell model for raster images and Recraft's V3 SVG model for vector graphics, allowing your AI assistant to create visual content on demand.
Before starting, you'll need:
The quickest way to run the MCP server is using NPX:
env REPLICATE_API_TOKEN=your_token_here npx -y replicate-flux-mcp
Replace your_token_here
with your actual Replicate API token.
.cursor/mcp.json
in your project directory:{
"mcpServers": {
"replicate-flux-mcp": {
"command": "env REPLICATE_API_TOKEN=YOUR_TOKEN npx",
"args": ["-y", "replicate-flux-mcp"]
}
}
}
YOUR_TOKEN
with your actual Replicate API tokenenv REPLICATE_API_TOKEN=YOUR_TOKEN npx -y replicate-flux-mcp
Create or edit the mcp.json
file in your configuration directory:
{
"mcpServers": {
"replicate-flux-mcp": {
"command": "npx",
"args": ["-y", "replicate-flux-mcp"],
"env": {
"REPLICATE_API_TOKEN": "YOUR_TOKEN"
}
}
}
}
If you prefer not to run the server locally, you can use the hosted versions:
To generate an image, simply ask your AI assistant naturally:
Can you generate an image of a serene mountain landscape at sunset?
The assistant will use the generate_image
tool to create the image.
You can customize image generation with parameters:
Please create a high-resolution image of a space station with a 16:9 aspect ratio
Generates a single image from a text prompt:
{
"prompt": "A cyberpunk cityscape at night with neon lights",
"aspect_ratio": "16:9",
"output_format": "png"
}
Parameters:
prompt
(required): Text description of desired imageseed
(optional): For reproducible resultsgo_fast
(optional): Run faster predictions (default: true)megapixels
(optional): Resolution - "1" or "0.25" (default: "1")num_outputs
(optional): Number of images (1-4)aspect_ratio
(optional): Image dimensions ratio (default: "1:1")output_format
(optional): "webp", "jpg", or "png" (default: "webp")output_quality
(optional): Image quality 0-100 (default: 80)num_inference_steps
(optional): Denoising steps 1-4 (default: 4)disable_safety_checker
(optional): Disable safety filter (default: false)Creates vector graphics in SVG format:
{
"prompt": "A minimalist logo for a tech company",
"size": "1024x1024",
"style": "line_art"
}
Parameters:
prompt
(required): Text description of desired SVGsize
(optional): Size of output (default: "1024x1024")style
(optional): Style options - "any", "engraving", "line_art", "line_circuit", "linocut" (default: "any")Creates multiple images from different prompts:
{
"prompts": [
"A red sports car on a mountain road",
"A blue sports car on a beach",
"A vintage sports car in a city street"
],
"aspect_ratio": "16:9"
}
Creates variations of the same concept:
{
"prompt": "A futuristic city skyline",
"num_variants": 4,
"prompt_variations": [
"in watercolor style",
"as an oil painting",
"with neon lighting",
"during sunset"
]
}
You can access your generation history using these resources:
imagelist
: View your history of generated raster imagessvglist
: View your history of generated SVG imagespredictionlist
: Browse all your Replicate predictionsTo add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "replicate-flux-mcp" '{"command":"env REPLICATE_API_TOKEN=YOUR_TOKEN npx","args":["-y","replicate-flux-mcp"]}'
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": {
"replicate-flux-mcp": {
"command": "env REPLICATE_API_TOKEN=YOUR_TOKEN npx",
"args": [
"-y",
"replicate-flux-mcp"
]
}
}
}
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.json
2. Add this to your configuration file:
{
"mcpServers": {
"replicate-flux-mcp": {
"command": "env REPLICATE_API_TOKEN=YOUR_TOKEN npx",
"args": [
"-y",
"replicate-flux-mcp"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect