Replicate Ideogram V3 Balanced

Provides access to the Ideogram V3 Balanced model via Replicate through an MCP server for text-to-image generation, inpainting, and style transfer.

javascript

GitHub Stars

javascript

Language

4 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": {
    "pierrunoyt-replicate-ideogram-v3-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/PierrunoYT/replicate-ideogram-v3-mcp-server.git"
      ],
      "env": {
        "REPLICATE_API_TOKEN": "YOUR_REPLICATE_API_TOKEN"
      }
    }
  }
}

This MCP server exposes the ideogram-v3-balanced image generation model from Replicate, enabling you to generate high-quality images directly through your MCP client. It supports text-to-image generation, inpainting, style transfer, extensive aspect ratios and resolutions, reproducible results with seeds, and automatic local storage of generated outputs.

How to use

You connect your MCP client to a local or remote MCP server that provides access to the Ideogram V3 Balanced model. Use the server to submit image generation requests, monitor their status, and retrieve the resulting image URLs and local copies. You can control prompts, choose aspect ratios or specific resolutions, apply styles and reference images, enable inpainting with an image and mask, and use seeds for reproducible results. When a request completes, you receive the generated image URLs along with details of all parameters used.

How to install

Prerequisites you need before installing: Node.js and npm (or a compatible runtime for your chosen installation method). Ensure your environment can run external commands and access the internet to fetch model services.

# Quick start with universal npx installation (no local setup required)
npx -y https://github.com/PierrunoYT/replicate-ideogram-v3-mcp-server.git

If you prefer a local installation, clone the project, install dependencies, and build the project.

git clone https://github.com/PierrunoYT/replicate-ideogram-v3-mcp-server.git
cd replicate-ideogram-v3-mcp-server
npm install
npm run build

Additional configuration and usage notes

Environment variable you must set for API access: REPLICATE_API_TOKEN. This token authorizes access to the Replicate service and the Ideogram V3 Balanced model.

If you run the server via MCP client configuration, you will typically provide the runtime command and any necessary environment variables. The server examples below show two common ways to start the MCP server: via npx for a quick start, or via a local node runtime after building.

Available tools

generate_image

Generate images using the Ideogram V3 Balanced model with comprehensive parameter support including prompt, aspect_ratio, resolution, style_type, style_preset, seed, and inpainting options.

get_image_status

Check the status of an image generation request using a prediction_id and retrieve final image URLs when complete.

inpainting

Edit existing images by supplying an image and a mask to apply targeted changes based on the prompt.

style_transfer

Apply style transfer using style_type, style_preset, and optional style_reference_images to guide the aesthetic.

predict_status

Monitor the progress of a running generation task and retrieve logs and results when finished.

Built by

VeilStrat

AI signals for GTM teams