Replicate Des

Provides an MCP server to generate images via Replicate Flux 1.1 Pro with flexible token handling.
  • javascript

0

GitHub Stars

javascript

Language

5 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": {
    "noeltg77-replicate-designer": {
      "command": "mcp-replicate-designer",
      "args": [],
      "env": {
        "REPLICATE_API_TOKEN": "your_replicate_api_token_here"
      }
    }
  }
}

This MCP server lets you generate images using Replicate's Flux 1.1 Pro model. You can run it locally or via an automated agent, and it exposes a single tool for image generation. Use it to integrate image synthesis into your workflows or chat assistants with flexible token handling and transport options.

How to use

You interact with this MCP server through an MCP client or an agent that can talk to multiple MCPs. You enable the server, then issue the generate_image tool calls with your desired prompts and options. The server handles token management and transports, so you can focus on constructing prompts and adjusting image settings like aspect ratio and format.

How to install

Prerequisites you need to have installed before you run the MCP server:

  • Python 3.9+ (for pip-based installation)
  • Node.js 14+ (for npx-based usage)
  • Git (for local cloning)

Option A: Install directly with pip and run the MCP server locally

pip install git+https://github.com/yourusername/replicate-designer.git

Then start the MCP server:

mcp-replicate-designer

Option B: Use npx with a GitHub repository (preferred for token in config)

# Create a configuration file mcps.json as shown below
{
  "mcpServers": {
    "replicateDesigner": {
      "command": "npx",
      "args": [
        "-y", 
        "github:yourusername/replicate-designer"
      ],
      "env": {
        "REPLICATE_API_TOKEN": "your_replicate_api_token_here"
      }
    }
  }
}

Then run the MCP client with the configuration file:

npx @anthropic-ai/assistant --mcps-json mcps.json

Option C: Install locally from source and run from the installed package

git clone https://github.com/yourusername/replicate-designer.git
cd replicate-designer
pip install -e .

Then start the MCP server (if you have a standard start script available after installation):

mcp-replicate-designer

Additional configuration and usage notes

The MCP server can be provided with an API token via environment variables, config files, or a project-local .env file. Use the following patterns to ensure your token is securely supplied without committing it to source control.

# Example environment variable usage
export REPLICATE_API_TOKEN=your_api_token_here
# Example .env file
REPLICATE_API_TOKEN=your_api_token_here

Tool

generate_image Generates an image using Replicate's Flux 1.1 Pro model.

Security notes

Guard your API tokens. Do not commit tokens to public repositories. Use environment variables or secret management when possible, especially in shared environments or CI pipelines.

Examples

Example tool invocation with a prompt and options to generate a 1:1 webp image.

{
  "prompt": "A photograph of an humanoid AI agent looking sad and in disrepair, the agent is sat at a workbench getting fixed by a human male",
  "aspect_ratio": "1:1",
  "output_format": "webp"
}

Available tools

generate_image

Generates an image using Replicate's Flux 1.1 Pro model. Takes parameters like prompt, aspect_ratio, output_format, output_quality, safety_tolerance, and prompt_upsampling to control the result.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
Replicate Des MCP Server - noeltg77/replicate-designer | VeilStrat