Replicate

Provides Python-based MCP access to Replicate image generation models via a local server with schema inspection, generation, and output optimization.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 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": {
    "mcp-mirror-tzafrir_mcp-server-replicate": {
      "command": "fastmcp",
      "args": [
        "dev",
        "server.py"
      ],
      "env": {
        "REPLICATE_API_TOKEN": "your_token_here"
      }
    }
  }
}

You have a FastMCP server that exposes Replicate’s AI models through a simple, standardized interface. It lets you access image generation models hosted on Replicate via a local MCP server, so you can integrate AI-powered image creation into your workflows with consistent tooling and easy client access.

How to use

Start by configuring your API token and launching the server. Once the server is running, you can connect an MCP client to request image generation models, inspect model schemas, and adjust generation parameters. The server handles interaction with Replicate behind a consistent interface, so you can plug in your existing MCP client workflows for image creation, resizing, and optimization.

How to install

Prerequisites: you need Python installed on your system. Ensure you have a working Python 3.x environment and pip available.

Install dependencies and set up the token, then start the server using the commands below.

pip install -r requirements.txt

# Create or edit the environment file with your Replicate API token
REPLICATE_API_TOKEN=your_token_here

# Run the MCP server locally
fastmcp dev server.py

Additional content

Project status: Early Alpha. Features and APIs may change as the project evolves.

Current capabilities focus on image generation models: you can inspect model schemas, generate images with customizable parameters, and perform output resizing and optimization.

Security and usage notes: protect your Replicate API token. Do not expose the token in client-side code or public repositories. Use a dedicated environment configuration file and secure storage for tokens.

Available tools

model_schema_inspection

Inspect model schemas for image generation to understand available parameters and constraints.

generate_image

Generate images using selected Replicate models with customizable parameters.

resize_output

Resize and optimize generated images for preferred output size and quality.