MCP Replicate FLUX
[](https://smithery.ai/server/@andylee20014/mcp-replicate-flux)
A Model Context Protocol (MCP) server that generates images using Replicate's FLUX model and stores them in Cloudflare R2.
Replicate FLUX Cloudflare R2 MCP
Features
- Generate images using Replicate's black-forest-labs/flux-schnell model
- Store generated images in Cloudflare R2
- Return accessible image URLs
- Support for custom prompts and filenames
- Replicate black-forest-labs/flux-schnell
- Cloudflare R2
Prerequisites
- Node.js (v16 or higher)
- Replicate API token
- Cloudflare R2 bucket and credentials
- npm or yarn
- Node.js v16
- Replicate API
- Cloudflare R2
- npm yarn
Environment Variables
Required environment variables in `.env` file:
`.env`
Local Installation
Installing via Smithery
To install MCP Replicate FLUX for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@andylee20014/mcp-replicate-flux):
Installing manually
Follow these steps to set up the project locally:
Make sure your Cloudflare R2 bucket has appropriate CORS settings for public access to the uploaded images.
Running Locally
To start the MCP server locally:
The server will start and listen for MCP protocol messages on standard input/output.
Usage
The server provides a `generate-image` tool that accepts two parameters:
- `prompt`: The text prompt for image generation
- `filename`: The desired filename for the generated image `generate-image`
- `prompt`
- `filename`
Integration Example
Here's an example of how to integrate with this MCP server using the MCP client library:
Example response
Testing
A test script is provided to verify the image generation and upload functionality.
Running the test
The test script will:
- Generate an image with a sample prompt
- Upload the image to Cloudflare R2
- Return the accessible URL
- Cloudflare R2
- URL
Example test output
You can modify the prompt in `test.js` to test different image generation scenarios.
Cursor MCP Configuration Cursor MCP
There are two ways to configure the MCP server in Cursor:
Cursor MCP
Method 1: Complete Configuration
Create a file at `~/.cursor/mcp.json` with all environment variables:
`~/.cursor/mcp.json`
Method 2: Minimal Configuration
If you prefer to manage environment variables separately (using system environment variables or .env file), you can use a minimal configuration:
When using the minimal configuration, make sure your environment variables are properly set up either in:
- System environment variables
- `.env` file in the project directory
- Cloud platform's environment variables (for deployed servers)
- `.env`
Notes
- The `description` field is optional in both methods
- Environment variables in the configuration file take precedence over system environment variables
- After changing the configuration, restart Cursor to apply the changes
- `description`
- Cursor
Project Structure
Troubleshooting
Common Issues
- **Image generation fails**: Check your Replicate API token and quota
- **R2 upload fails**: Verify your R2 credentials and bucket permissions
- **Cannot access generated images**: Ensure your R2 bucket has proper CORS configuration
- ** ** Replicate API
- **R2 ** R2
- ** ** R2 CORS
MCP Protocol
The Model Context Protocol (MCP) is a standard for AI model interaction that enables interoperability between different AI systems. This server implements an MCP tool that can be used with any MCP-compatible client.
For more information about MCP, visit: [https://mcp.freeaigen.com/](https://mcp.freeaigen.com/)
References
- [Model Context Protocol Documentation](https://mcp.freeaigen.com/)
- [Replicate API Documentation](https://replicate.com/docs)
- [Cloudflare R2 Documentation](https://developers.cloudflare.com/r2/)
- [Flux AI Model](https://replicate.com/black-forest-labs/flux-schnell)
License
MIT