This MCP server provides image generation capabilities through the Replicate Flux model. It allows Claude to create images from text descriptions using a simple API interface.
The easiest installation method is through Smithery:
npx -y @smithery/cli install @GongRzhe/Image-Generation-MCP-Server --client claude
You can use the package directly from npm without installing it locally.
If you prefer a local installation:
# Global installation
npm install -g @gongrzhe/image-gen-server
# Or local installation
npm install @gongrzhe/image-gen-server
Edit your Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%/Claude/claude_desktop_config.json
This method runs the server directly from npm without needing local files:
{
"mcpServers": {
"image-gen": {
"command": "npx",
"args": ["@gongrzhe/image-gen-server"],
"env": {
"REPLICATE_API_TOKEN": "your-replicate-api-token",
"MODEL": "alternative-model-name"
},
"disabled": false,
"autoApprove": []
}
}
}
If you installed the package locally:
{
"mcpServers": {
"image-gen": {
"command": "node",
"args": ["/path/to/image-gen-server/build/index.js"],
"env": {
"REPLICATE_API_TOKEN": "your-replicate-api-token",
"MODEL": "alternative-model-name"
},
"disabled": false,
"autoApprove": []
}
}
}
your-replicate-api-token
in the MCP settingsREPLICATE_API_TOKEN
(required): Your Replicate API token for authenticationMODEL
(optional): The Replicate model to use for image generation. Defaults to "black-forest-labs/flux-schnell"disabled
: Controls whether the server is enabled (false
) or disabled (true
)autoApprove
: Array of tool names that can be executed without user confirmation. Empty array means all tool calls require confirmation.This tool generates images using the Flux model based on text prompts.
prompt
(required): Text description of the image to generateseed
(optional): Random seed for reproducible generationaspect_ratio
(optional): Image aspect ratio (default: "1:1")output_format
(optional): Output format - "webp", "jpg", or "png" (default: "webp")num_outputs
(optional): Number of images to generate (1-4, default: 1)const result = await use_mcp_tool({
server_name: "image-gen",
tool_name: "generate_image",
arguments: {
prompt: "A beautiful sunset over mountains",
aspect_ratio: "16:9",
output_format: "png",
num_outputs: 1
}
});
The tool returns an array of URLs to the generated images.
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 > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.