Gemini Watermark Remover MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add gemini-watermark-remover -- npx -y gemini-watermark-remover-mcp
README.md

MCP server for removing Gemini AI watermarks from generated images.

Gemini Watermark Remove MCP Server

MCP server for removing Gemini AI watermarks from generated images.

Local Stdio Mode

[!CAUTION]

Due to sharp compilation limitations, if you are on Linux or MacOS, it is recommended to globally install it so that it can run properly.

npm install -g gemini-watermark-remover-mcp

Claude Desktop

{
  "mcpServers": {
    "gemini-watermark-remove": {
      "command": "npx",
      "args": ["-y", "gemini-watermark-remover-mcp"]
    }
  }
}

OpenCode

{
  "mcp": {
    "gemini-watermark-remove": {
      "command": ["npx", "-y", "gemini-watermark-remover-mcp"],
      "type": "local",
      "enabled": true
    }
  }
}

Development

Prerequisites

  • Node.js >= 22
  • npm

Installation

# Clone or download the project
cd gemini-watermark-remover-mcp

# Install dependencies
npm install

# Build the project
npm run build

Running

Development mode (hot reload):

npm run dev

Production mode:

npm start
# or
node dist/index.js

Local Development Debug Config

For debugging after modifying source code, you can use the locally built version:

Claude Desktop:

{
  "mcpServers": {
    "gemini-watermark-remove": {
      "command": "node",
      "args": ["/path/to/gemini-watermark-remover-mcp/dist/index.js"]
    }
  }
}

MCP Tool Usage

gemini_remove_watermark

Removes the Gemini AI watermark from generated images.

Parameters:

Parameter Type Required Default Description
input_path string Yes - Input image path (PNG, JPG, WEBP)
output_path string Yes - Output image path
response_format string No markdown Output format: markdown or json
jpeg_quality number No 95 JPEG quality (1-100)
webp_quality number No 80 WEBP quality (1-100)
png_compression_level number No 6 PNG compression level (0-9)

License

This project is licensed under the MIT License

Acknowledgments

This project is based on journey-ad/gemini-watermark-remover.

Thanks for the original implementation!

Tools (1)

gemini_remove_watermarkRemoves the Gemini AI watermark from generated images.

Configuration

claude_desktop_config.json
{"mcpServers": {"gemini-watermark-remove": {"command": "npx", "args": ["-y", "gemini-watermark-remover-mcp"]}}}

Try it

Remove the Gemini watermark from the image located at ./downloads/gemini_image.png and save it to ./cleaned/clean_image.png.
Clean the watermark from my generated image at ./input.jpg, using a JPEG quality of 90.
Process the image at ./art.webp to remove the watermark, outputting the result in JSON format.

Frequently Asked Questions

What are the key features of Gemini Watermark Remover?

Removes Gemini AI watermarks from images. Supports PNG, JPG, and WEBP formats. Configurable JPEG and WEBP quality settings. Adjustable PNG compression levels. Supports both markdown and JSON response formats.

What can I use Gemini Watermark Remover for?

Cleaning up AI-generated images for professional presentations or portfolios. Batch processing images to remove watermarks for cleaner visual assets. Preparing Gemini-generated content for use in projects where watermarks are not desired.

How do I install Gemini Watermark Remover?

Install Gemini Watermark Remover by running: npx -y gemini-watermark-remover-mcp

What MCP clients work with Gemini Watermark Remover?

Gemini Watermark Remover works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Gemini Watermark Remover docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare