Flux Image MCP Server
Generate images using Replicate's Flux Schnell model.
Flux Image MCP Server
This MCP server provides image generation capabilities using the Flux Schnell model on Replicate.
Installation
- Install the MCP SDK globally:
npm install -g @modelcontextprotocol/sdk@latest
- Clone this repository to your MCP servers directory:
cd ~/Documents/Cline/MCP
git clone https://github.com/yourusername/flux-img-mcp.git
cd flux-img-mcp
npm install
- Build the server:
npm run build
- Add the server configuration to your MCP settings file (either global or workspace):
{
"mcpServers": {
"flux-img": {
"command": "node",
"args": ["/path/to/flux-img-mcp/build/index.js"],
"env": {
"REPLICATE_API_TOKEN": "your-replicate-api-token"
},
"disabled": false,
"alwaysAllow": []
}
}
}
Configuration
The server requires the following environment variable:
REPLICATE_API_TOKEN: Your Replicate API token. You can get this from your Replicate account settings.
Usage
Once installed and configured, the server provides the following tool:
generate_image
Generates an image using the Flux Schnell model based on a text prompt.
Parameters:
prompt(string, required): Text description of the desired image
Example usage:
<use_mcp_tool>
<server_name>flux-img</server_name>
<tool_name>generate_image</tool_name>
<arguments>
{
"prompt": "A beautiful sunset over mountains"
}
</arguments>
</use_mcp_tool>
The tool will return a JSON response containing:
status: The status of the generation requestoutput: The URL of the generated image (if successful)error: Any error message (if failed)
Development
To make changes to the server:
- Modify the source code in
src/index.ts - Rebuild the server:
npm run build - Restart the MCP server for changes to take effect
Error Handling
The server includes comprehensive error handling for:
- Missing API token
- Invalid parameters
- API request failures
- Network issues
Security
- Never commit your Replicate API token to version control
- Always provide the token through environment variables
- The server validates all input parameters before making API requests
Related Servers
ADM1 MCP Server
Control anaerobic digestion modeling (ADM1) using natural language.
LGTM Dog MCP
Generates dog images with an LGTM (Looks Good To Me) overlay using the Dog CEO API.
Image
Fetch and process images from URLs, local file paths, and numpy arrays, returning them as base64-encoded strings.
Chess UCI
Connect to UCI-compatible chess engines like Stockfish to play and analyze games. Requires a local chess engine binary.
Soccerdata MCP Server
Provides real-time football match information from the SoccerDataAPI using natural language.
StockSpark MCP Server
An MCP server for AI-powered vehicle dealership management.
Haiguitang (Turtle Soup) Game
An MCP server for '海龟汤' (Turtle Soup), a scenario-based reasoning puzzle game.
MCP Goodnews
An MCP application that delivers curated positive and uplifting news stories using NewsAPI and Cohere LLM.
Text-to-Speech (TTS)
A Text-to-Speech server supporting multiple backends like macOS say, ElevenLabs, Google Gemini, and OpenAI TTS.
Weather API MCP Server
Provides current weather data and forecasts using the QWeather API.