# Mcp Changeimageto

> Image editing MCP for Cursor & Claude: remove background, blur BG, upscale, OCR, PDF, Gemini text edits, inpainting, bulk tools. Model Context Protocol.

- **Type:** MCP server
- **Install:** `agentstack add mcp-vipulawl-mcp-changeimageto`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [vipulawl](https://agentstack.voostack.com/s/vipulawl)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [vipulawl](https://github.com/vipulawl)
- **Source:** https://github.com/vipulawl/mcp-changeimageto
- **Website:** https://www.changeimageto.com

## Install

```sh
agentstack add mcp-vipulawl-mcp-changeimageto
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# ChangeImageTo MCP — Image editing for Cursor, Claude & any MCP client

[](https://modelcontextprotocol.io/)
[](https://www.python.org/downloads/)
[](LICENSE)
[](https://www.changeimageto.com/)
[](https://fastapi.tiangolo.com/)

**A production-ready [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) server for AI-assisted image editing.** Give [Cursor](https://cursor.com/), [Claude Desktop](https://claude.ai/download), [Windsurf](https://codeium.com/windsurf), [VS Code MCP](https://code.visualstudio.com/), and other MCP hosts **16 tools** to remove backgrounds, blur or grayscale backgrounds, change colors, convert formats (PNG/JPEG/WebP/…), upscale, denoise/enhance, run **OCR**, export **PDF**, edit text in images (**Gemini**), clean watermarks, inpaint masked regions, and run **bulk** resize / convert / quality checks.

> **Search-friendly aliases:** image editing MCP · MCP image tools · background removal MCP · remove background API MCP · photo editing LLM tools · Cursor image MCP · Claude image MCP · batch image processing MCP · image upscaling MCP · OCR MCP server.

The server is a **small HTTP client**: it forwards requests to the same **ChangeImageTo** image API used by [changeimageto.com](https://www.changeimageto.com/). Point it at the hosted backend (default) or at your own deployment of the matching `/api/*` routes.

---

## Why this repo?

| You want… | This MCP provides… |
|-----------|-------------------|
| **Remove background** / transparent PNG | `remove_background` |
| **Portrait / product** cutouts | `category`: `product` or `portrait` |
| **Blur background** (bokeh-style) | `blur_background` |
| **Grayscale background** only | `grayscale_background` |
| **Color grading** (hue / saturation / brightness / contrast) | `change_image_color` |
| **Convert image format** | `convert_image_format` |
| **Upscale** 2× / 3× / 4× | `upscale_image` |
| **Sharpen / denoise / deblur** | `enhance_image` |
| **Strip text** from photos | `remove_text_from_image` |
| **Remove Gemini watermark** | `remove_gemini_watermark` |
| **Replace text** in an image (AI) | `edit_text_in_image` |
| **Image → PDF** | `image_to_pdf` |
| **Image → text (OCR)** | `image_to_text_ocr` |
| **Inpaint** with a user mask | `remove_painted_areas` |
| **Bulk** resize / convert / quality | `bulk_*` tools |

---

## GitHub topics (repository tags)

GitHub allows **20 topics** per repository. This repo’s topics (for search and discoverability):

`mcp` · `model-context-protocol` · `mcp-server` · `image-editing` · `image-processing` · `background-removal` · `remove-background` · `photo-editing` · `image-tools` · `cursor` · `claude` · `claude-desktop` · `llm` · `ai-tools` · `python` · `ocr` · `image-upscaling` · `inpainting` · `fastapi` · `changeimageto`

---

## Install

```bash
git clone https://github.com/vipul510-web/mcp-changeimageto.git
cd mcp-changeimageto
python3 -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
pip install .
```

Install from Git without cloning:

```bash
pip install git+https://github.com/vipul510-web/mcp-changeimageto.git
```

---

## Cursor, Claude Desktop, VS Code — MCP config

Replace paths with yours:

```json
{
  "mcpServers": {
    "changeimageto": {
      "command": "/full/path/to/mcp-changeimageto/.venv/bin/python",
      "args": ["/full/path/to/mcp-changeimageto/server.py"],
      "env": {
        "CHANGEIMAGETO_API_BASE": "https://bgremover-backend-121350814881.us-central1.run.app"
      }
    }
  }
}
```

Or use the console script after `pip install .`:

```json
{
  "mcpServers": {
    "changeimageto": {
      "command": "/full/path/to/.venv/bin/mcp-changeimageto"
    }
  }
}
```

The entrypoint runs `mcp.run()` (stdio transport).

---

## Environment variables

| Variable | Default | Meaning |
|----------|---------|---------|
| `CHANGEIMAGETO_API_BASE` | `https://bgremover-backend-121350814881.us-central1.run.app` | API origin (no trailing slash). Matches the backend used by [changeimageto.com](https://www.changeimageto.com/) (the marketing site does **not** serve `/api/*` itself). |
| `CHANGEIMAGETO_HTTP_TIMEOUT` | `180` | HTTP timeout in seconds. |
| `CHANGEIMAGETO_API_TOKEN` | — | Optional `Authorization: Bearer` header if your self-hosted API requires it. |

---

## Image inputs

Each tool accepts `image` (or a **list** for bulk tools) as:

- **HTTPS URL** to an image  
- **Local file path**  
- **Data URL:** `data:image/png;base64,...`

Responses that are binary (PNG, JPEG, PDF, ZIP) are returned as JSON with **`data_base64`** when the payload is under ~12 MB. Larger outputs omit base64 and include a short notice—use a local API, smaller files, or non-bulk endpoints.

---

## Tools ↔ REST API

| MCP tool | HTTP |
|----------|------|
| `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` |

Test-only, blog, analytics, and payment endpoints are **not** wrapped (by design).

---

## Related

- **Product & docs:** [changeimageto.com](https://www.changeimageto.com/)  
- **MCP spec:** [modelcontextprotocol.io](https://modelcontextprotocol.io/)  
- **Issues & ideas:** [github.com/vipul510-web/mcp-changeimageto/issues](https://github.com/vipul510-web/mcp-changeimageto/issues)

---

## License

MIT

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [vipulawl](https://github.com/vipulawl)
- **Source:** [vipulawl/mcp-changeimageto](https://github.com/vipulawl/mcp-changeimageto)
- **License:** MIT
- **Homepage:** https://www.changeimageto.com

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-vipulawl-mcp-changeimageto
- Seller: https://agentstack.voostack.com/s/vipulawl
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.