ChangeImageTo MCP
The official Model Context Protocol server for ChangeImageTo. Use natural language in Cursor, Claude Desktop, VS Code, or any MCP-compatible client to run the same image engines as changeimageto.com.
What you get
Sixteen tools map one-to-one to our production REST API. Processing runs on the same backend that powers the website (configurable via environment variable if you self-host).
- Cutouts & backgrounds: remove background, blur background, grayscale background, solid color / composite backgrounds
- Adjust & convert: color adjustments, format conversion (PNG, JPEG, WebP, and more), upscaling, denoise / sharpen / enhance
- Text & cleanup: OCR (image to text), remove detected text, Gemini-powered text replacement, Gemini watermark cleanup, mask inpainting
- Documents & batch: image to PDF, bulk resize, bulk convert, bulk image quality scoring
Install
Python 3.10+. From a clone of the repo:
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install .
Or install directly from Git:
pip install git+https://github.com/vipul510-web/mcp-changeimageto.git
Cursor / Claude Desktop (example)
Add an MCP server entry pointing at server.py or the mcp-changeimageto console script. Set the API base to our Cloud Run backend (default in the package) or your own deployment:
{
"mcpServers": {
"changeimageto": {
"command": "/path/to/mcp-changeimageto/.venv/bin/python",
"args": ["/path/to/mcp-changeimageto/server.py"],
"env": {
"CHANGEIMAGETO_API_BASE": "https://bgremover-backend-121350814881.us-central1.run.app"
}
}
}
}
CHANGEIMAGETO_API_BASE.
Tool reference
| MCP tool | API |
|---|---|
remove_background | POST /api/remove-bg |
blur_background | POST /api/blur-background |
grayscale_background | POST /api/grayscale-background |
change_image_color | POST /api/change-color |
convert_image_format | POST /api/convert-format |
upscale_image | POST /api/upscale-image |
enhance_image | POST /api/enhance-image |
remove_text_from_image | POST /api/remove-text |
remove_gemini_watermark | POST /api/remove-gemini-watermark |
edit_text_in_image | POST /api/edit-text-in-image |
image_to_pdf | POST /api/image-to-pdf |
image_to_text_ocr | POST /api/image-to-text |
remove_painted_areas | POST /api/remove-painted-areas |
bulk_resize_images | POST /api/bulk-resize |
bulk_convert_images | POST /api/bulk-convert-format |
bulk_quality_check | POST /api/bulk-quality-check |
Images may be passed as a URL, local path, or base64 data URL. Binary results are returned as JSON with base64 when under the size limit.
More documentation & topics
Full README, environment variables, and GitHub topics for discovery: github.com/vipul510-web/mcp-changeimageto