Image-Toolbox-MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Image-Toolbox-MCPcompress all the PNGs in ./screenshots and convert them to webp"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Image-Toolbox-MCP_By-Cowlsly
An open-source Model Context Protocol (MCP) integration for Image Toolbox, enabling AI assistants to access image conversion, editing, compression, metadata, and batch-processing workflows. Developed by Cowlsly as an independent integration with attribution to the original project.
Status: early development. A minimal MCP server works with seven tools:
image_inspect(read-only),image_convert(JPEG/PNG/WebP),image_resize,image_compress,image_rotate_flip,image_cropandimage_batch(one operation on a whole folder). See roadmap.md and docs/PROJECT_STATE.md.
Attribution
Image Toolbox is an Android image editor by T8RIN (Malik Mukhametzyanov), licensed under Apache-2.0. This project is independent and is not affiliated with or endorsed by the Image Toolbox authors. It currently contains no Image Toolbox source code; image processing is done by its own Python engine built on Pillow. See docs/audit/upstream-audit.md.
Related MCP server: Image Processing MCP Server
How it works
Python 3.10+ server, Pillow image engine, official MCP Python SDK over stdio. Rationale: ADR-0001.
You choose one input folder; the server can only read images inside it. Paths with .., symbolic links, and absolute paths outside the folder are refused. Originals are never modified. New files go into one output folder (default imagetoolbox-out inside the input folder, or --out DIR); existing files are never overwritten — a -1, -2… suffix is added instead. There are no shell, network or general file tools. Output rules: ADR-0002.
Tool | What it does |
| Format, width/height, colour mode, alpha, frames, file size, orientation, a safe EXIF subset. GPS is never returned — only whether it is present. |
| Convert to |
| Resize by |
| Make a file smaller. JPEG/WebP: |
|
|
| Either a box — |
| Apply one |
Format limits: JPEG has no transparency (it is filled with white and a warning is returned); converting a JPEG to PNG/WebP does not bring back detail already lost; animated images are converted from their first frame only.
Run it (an MCP client normally launches this for you):
imagetoolbox-mcp --root ~/Pictures # or: IMAGETOOLBOX_MCP_ROOT=~/Pictures imagetoolbox-mcp
imagetoolbox-mcp --root ~/Pictures --out ~/Pictures/converted # optional output folder (or IMAGETOOLBOX_MCP_OUT)Using it from an Android phone (Termux + Claude Code or Gemini CLI), and why the Claude/ChatGPT apps can't connect yet: docs/clients.md.
Example client config (mcpServers style, used by many desktop clients):
{ "mcpServers": { "imagetoolbox": { "command": "imagetoolbox-mcp", "args": ["--root", "/path/to/images"] } } }Install and test (developers)
python -m pip install -e . # Python 3.10+; pulls in pillow and mcp
python -m unittest discover -s tests -t .
imagetoolbox-mcp --versionLint: ruff check src tests && ruff format --check src tests.
Termux (Android): pkg install python python-pillow, then pip install mcp — still being verified, see docs/PROJECT_STATE.md. More in CONTRIBUTING.md; security reports: SECURITY.md.
Licence
MIT. See LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Image and video AI tools and your own pipelines, run from any AI assistant.
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
- MochifyOAuthapp.mochify
Image and PDF toolkit: convert to AVIF/WebP/JXL, resize, crop, remove backgrounds, optimize PDFs.
Image processing for AI agents: resize, convert, compress, crop, and web-ready AI-generated images.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables text-to-image generation, style transfer, background removal, and automatic image cropping using Google's Imagen AI models through the Model Context Protocol.-
- AlicenseNot gradedqualityBmaintenanceEnables image processing tasks such as resizing, compressing, converting formats, cropping, and extracting metadata directly within IDEs like Cursor via the Model Context Protocol.19 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to generate and edit images using Azure OpenAI's gpt-image-1 model through the Model Context Protocol.3MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI image processing tools such as vectorization, background removal, upscaling, and logo generation from any MCP-compatible client like Claude Code or Cursor.12 npmMIT