Image Toolbox的开源模型上下文协议（MCP）集成，使AI助手能够访问图像转换、编辑、压缩、元数据和批量处理等工作流程。
概览
Image Toolbox的开源模型上下文协议（MCP）集成，使AI助手能够访问图像转换、编辑、压缩、元数据和批处理等工作流程。由Cowlsly开发，作为独立集成，归属于原始项目。 目前还没有可用的MCP服务器。请参见 roadmap.md 和文档/PROJECT_STATE.md。 Image Toolbox 是一款由 Android 开发的图像编辑器，采用 Apache 2.0 许可。该项目独立，与 Image Toolbox 作者无任何关联或认可。目前包含 Image Toolbox 源代码;图像处理由其基于 Pillow 构建的 Python 引擎完成。参见 docs/audit/upstream-audit.md。 Python 3.10+ 服务器，Pillow image engine，官方 MCP Python SDK 通过 stdio 运行。理由：ADR-0001。 Termux（Android）：pkg install python python-pillow，然后 pip install mcp — 仍在验证中，详见 docs/PROJECT_STATE.md。更多内容见 CONTRIBUTING.md;安全报告：SECURITY.md。
概述（AI 翻译）
Image Toolbox的开源模型上下文协议（MCP）集成，使AI助手能够访问图像转换、编辑、压缩、元数据和批处理等工作流程。由Cowlsly开发，作为独立集成，归属于原始项目。
状态：早期开发。 一个最小的MCP服务器可使用七种工具：
image_inspect（只读）、image_convert（JPEG/PNG/WebP）、image_resize、image_compress、image_rotate_flip、image_crop和image_batch（对整个文件夹操作一次）。参见 roadmap.md 和docs/PROJECT_STATE.md。
署名
Image Toolbox 是由 T8RIN（Malik Mukhametzyanov） 开发的 Android 图像编辑器，采用 Apache 2.0 许可。该项目独立，未与 Image Toolbox 作者有任何关联或认可。目前包含无 Image Toolbox 源代码;图像处理由其基于 Pillow 的 Python 引擎完成。参见 docs/audit/upstream-audit.md。
它是如何运作的
Python 3.10+ 服务器，Pillow image engine，官方 MCP Python SDK 通过 stdio 运行。理由：ADR-0001。
你选择一个输入文件夹;服务器只能读取其中的图像。路径带有“…
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
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.
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 |
|---|---|
image_inspect |
Format, width/height, colour mode, alpha, frames, file size, orientation, a safe EXIF subset. GPS is never returned — only whether it is present. |
image_convert |
Convert to jpeg, png or webp (quality 1–100, WebP lossless). Applies EXIF rotation, removes EXIF/GPS, keeps the colour profile. Optional output_name (no folders, no extension). |
image_resize |
Resize by width, height or both. fit: contain (default, keep aspect inside the box), cover (fill and centre-crop), exact (stretch). resample: lanczos (default), bicubic, bilinear, nearest (pixel art). Never enlarges unless allow_upscale. Keeps the source format (JPEG/PNG/WebP, else PNG) unless format is set. Same metadata rules as convert. Default name -x. |
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →配置
{ "mcpServers": { "imagetoolbox": { "command": "imagetoolbox-mcp", "args": ["--root", "/path/to/images"] } } }