mcp-server-replicate
MCP Server Replicate is a server designed to provide resource-based access for AI model inference through the Replicate API, particularly focused on image generation. It offers comprehensive features such as real-time updates, webhook integration, and secure API key management.
MCP Server Replicate
A FastMCP server implementation for the Replicate API, focusing on resource-based access to AI model inference with an emphasis on image generation.
Features
- Resource-based image generation and management
- Real-time updates through subscriptions
- Template-driven parameter configuration
- Comprehensive model discovery and selection
- Webhook integration for external notifications
- Quality and style presets for optimal results
- Progress tracking and status monitoring
- Secure API key management
Available Prompts
Text to Image (Primary)
Optimized for high-quality images from text descriptions with style control, quality presets, and customization.
Other Prompts
- Image to Image: Transform images
- Model Selection: Get help choosing models
- Parameter Help: Configure model parameters
Prerequisites
- Python 3.11 or higher
- Replicate API key
- UV for dependency management
Installation
- Via Smithery: Install with npx Smithery CLI
- Manually: Use UV, UVX, or pip
Claude Desktop Integration
Add and configure the server in Claude Desktop for image generation using natural language commands.
Troubleshooting
Check logs and configuration, ensure correct setup for Claude Desktop.
Development
Clone the repo, install dependencies, and run tests.
Contributing
Contributions welcome! See the Contributing Guide for details.
License
Project is licensed under the MIT License.