Replicate

MCP implementation to generate content using models hosted on Replicate

python

3

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "tzafrir-mcp-server-replicate": {
      "command": "fastmcp",
      "args": [
        "dev",
        "server.py"
      ],
      "env": {
        "REPLICATE_API_TOKEN": "YOUR_API_TOKEN"
      }
    }
  }
}

You run a FastMCP server that exposes Replicate’s AI models through a standardized interface, allowing you to access image generation capabilities from multiple models via MCP clients. It’s designed to be simple to start and connect to Replicate using a local server with a dedicated API token.

How to use

To use this MCP server, run it locally and connect your MCP client to the provided endpoint. The server acts as a bridge to Replicate, enabling image generation with configurable model parameters. You interact with the server just like other MCP endpoints: you request a model’s image generation capability, supply the desired parameters (such as prompt, width, height, and seed), and receive the generated image output. This setup is ideal for automation, pipelines, or integrating Replicate’s models into your own tooling.

How to install

Prerequisites: you need Python installed and access to the shell. You will also need a Replicate API token.

pip install -r requirements.txt

REPLICATE_API_TOKEN=your_token_here

fastmcp dev server.py

Available tools

model_schema_inspection

Inspect model schemas exposed by Replicate to understand available inputs and outputs for image generation.

image_generation

Submit image generation requests to Replicate models through the MCP bridge, with configurable prompts and parameters.

output_optimization

Resize and optimize the generated images for delivery and storage.