Provides tools for accessing AI models hosted on Replicate through a standardized interface, currently supporting image generation with model schema inspection, customizable parameters, and output optimization.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Server for Replicate generate an image of a futuristic city skyline at sunset"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A FastMCP server implementation for interfacing with Replicate's API. This server provides tools for accessing various AI models hosted on Replicate through a standardized interface.
This project is in early alpha development. Features and APIs may change significantly.
Image generation models with:
Model schema inspection
Image generation with customizable parameters
Output resizing and optimization
Related MCP server: Image Generation MCP Server
Text Generation
Support for text completion models
Chat model integration
Streaming support for real-time responses
Video Generation
Support for video generation models
Video output handling and optimization
Progress tracking for long-running generations
Additional Features
Model version management
Better error handling and retries
Caching for frequently used models
Rate limiting and queue management
Install dependencies:
pip install -r requirements.txtSet up your Replicate API token in .env:
REPLICATE_API_TOKEN=your_token_hereRun the server:
fastmcp dev server.pyThis server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Flux AI image generation
MCP server for Producer/Riffusion AI music generation
MCP server for Wan AI video generation
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tzafrir/mcp-server-replicate'
If you have feedback or need assistance with the MCP directory API, please join our Discord server