Image Processing MCP Server

MCP设计创作

提供方 rafael-castelo

设计创作 未标注 无需鉴权 社区 / 第三方 ClaudeCursor

一个提供图像处理功能的MCP服务器,支持批量调整大小、压缩、转换格式等操作,可直接集成到IDE中使用。

一句话选型结论

按资料字段整理

Image Processing MCP Server 属于设计创作类 MCP 服务器,传输方式未标注,无需鉴权,可直接接入 Claude、Cursor,没有现成安装命令,需按官方文档接入。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类设计创作 传输方式未标注 鉴权无需鉴权 部署方式未标注
GitHub 星标 1 仓库热度,无公开仓库时显示未标注
工具数 6 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

设计创作
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量6暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

图像处理TypeScript本地部署批量操作IDE集成格式转换图像压缩

安装与配置

未标注 无需鉴权
上游未给出传输方式
  1. 1
    准备运行环境

    按官方文档确认运行环境(常见为 Node.js 或 Python),装好后再执行安装命令。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 6 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
出图与素材

生成配图、图标与素材。

设计稿处理

读取设计稿、批量改尺寸或导出。

内容生成

按主题生成文案与视觉草稿。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 6 个工具,职责相对集中,接入后不容易误操作。
  • 已适配 Claude、Cursor,换客户端不用重新研究配置。
  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • 没有现成安装命令,需要按官方文档自己填启动命令和参数。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在设计创作场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Image Processing MCP Server当前 6 未标注 未标注 无 2026-05-17
Cursor Talk To Figma MCP Da1c7911 40 未标注 未标注 无 2026-05-17
Blender MCP 17 stdio · 本地进程 本地部署 有 2026-05-18
Nova Canvas MCP Server 2 stdio · 本地进程 本地部署 有 2026-05-17
Figma Context MCP 3aaa8d28 未标注 未标注 支持远程部署 无 2026-05-17
kreuzberg 未标注 stdio · 本地进程 本地部署 有 2026-04-12

服务器档案

设计创作
字段来自项目仓库与公开索引,中文说明由本站标注
提供方rafael-castelo上游标注的维护方 rafael-castelo
分类设计创作本站按上游分类展示
连接方式未标注上游未给出传输方式
鉴权方式无需鉴权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型未标注上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

6.4 KB
来自项目仓库与上游目录的原文,未做删改

Image Processing MCP server

Description

This project serves as an MCP (Model Context Protocol) server, offering a suite of tools for common image processing tasks. It enables applications and services, such as Cursor and Claude, to easily perform operations like resizing, compressing, and converting image formats directly within your IDE, streamlining your workflow without needing to switch contexts.

Example usage

Resize images in bulk:

Prompt:`` Resize all images insrc/assetsfolder to a height of 150px, store the resulting images with the_small` suffix


**Convert images format:**

Prompt:```
Convert all images with the `.jpeg` extension located in the `/media` directory to the `webp` format.
Save the converted images in the same directory.

Compress large images:

Prompt:`` Compress all images in the/src/images` directory that have a file size larger than 10MB.


## Features

-   **Resize Images:** Adjust the dimensions of images.
-   **Compress Images:** Reduce file size with configurable quality and lossless options.
-   **Convert Image Format:** Change image files between various formats (JPEG, PNG, WebP, AVIF, TIFF).
-   **Get Image Metadata:** Retrieve technical details and information about image files.
-   **Crop Images:** Extract a specified rectangular area from an image.

## Installation

To set up the project locally, follow these steps:

1.  **Prerequisites:** Ensure you have Node.js (version 14 or higher recommended) and npm installed on your system.
2.  **Clone the Repository:**```bash
    git clone git@github.com:rafael-castelo/image-processing-mcp-server.git
    cd image-processing-mcp
    ```

3.  **Install Dependencies:**```bash
    npm install
    ```

4. **Build:**```bash
    npm run build
    ```

    This will generate a build of the server and save it on ./build

## Usage

### Using from Cursor

Add or merge the following configuration to the `mcpServers` object:

NPX```json
    {
        "mcpServers": {
        "image-processing": {
                "command": "npx",
                "args": [
                    "-y",
                    "image-processing-mcp-server"
                ]
            }
        }
    }

LOCALjson { "mcpServers": { "image-processing": { "command": "node", "args": [ "path/to/mcp/server/build/index.js" ] } } }

Once this configuration is in place and Cursor is running, it will automatically start the image-processing MCP server, making the tools available for use via tool calls in the chat or other Cursor features that interact with MCP.

Tools Reference

This section details the image processing tools exposed by the MCP server, including their purpose and parameters.

resize-image

Description: Resize an image to a given width and height.

Parameters:

  • imagePath (string, required): Absolute path to the image file to be resized.
  • outputPath (string, required): Absolute path to save the resized image.
  • width (number, optional): Resulting width of the image. Optional if height is provided.
  • height (number, optional): Resulting height of the image. Optional if width is provided.
  • keepAspectRatio (boolean, optional): Whether to keep the original aspect ratio (default: false).
  • quality (number, optional): Compression quality (default: format standard, 1-100 for JPEG/WEBP, 0-9 for PNG).

compress-image

Description: Compress an image while preserving as much quality as possible. The original format is always kept.

Parameters:

  • imagePath (string, required): Absolute path to the image file to be compressed.
  • outputPath (string, required): Absolute path to save the compressed image.
  • quality (number, optional): Controls the trade-off between file size and visual quality. For JPEG, WebP, and AVIF, higher values (e.g., 90-100) mean better quality and larger files, while lower values (e.g., 60-80) reduce file size but may introduce visible artifacts.
  • lossless (boolean, optional): If true, uses lossless compression when supported by the format (e.g., PNG, WebP, AVIF). If false, lossy compression is used (default: true).

convert-image-format

Description: Convert an image to another format without losing quality. The tool always uses lossless conversion if supported by the output format. Supported formats: jpeg, jpg, png, webp, avif, tiff.

Parameters:

  • imagePath (string, required): Absolute path to the image file to be converted.
  • outputPath (string, required): Absolute path to save the converted image.
  • format (string, required): Desired output format (jpeg, jpg, png, webp, avif, tiff).

get-image-metadata

Description: Retrieves basic file information, including file size, format, dimensions in pixels (width and height), resolution, color space (e.g., sRGB, CMYK) and orientation details for a given image.

Parameters:

  • imagePath (string, required): Absolute path to the image file.

crop-image

Description: Crop an image to a specified rectangular area.

Parameters:

  • imagePath (string, required): Absolute path to the image file to be cropped.
  • outputPath (string, required): Absolute path to save the cropped image.
  • left (number, required): The x-coordinate of the top-left corner of the area to be cropped, in pixels.
  • top (number, required): The y-coordinate of the top-left corner of the area to be cropped, in pixels.
  • width (number, required): The width of the area to be cropped, in pixels.
  • height (number, required): The height of the area to be cropped, in pixels.

batch-image-processing

Description: Run multiple image processing tasks (resize, compress, get metadata, crop image or convert format) in a single batch operation. Always use this tool for tasks involving operations on more than one image.

Parameters:

  • operations (array of objects, required): An array of image processing operations to perform. Each object in the array should have two properties:
    • toolName (string, required): The name of the tool to run (resize-image, compress-image, convert-image-format, get-image-metadata, or crop-image).
    • options (object, required): An object containing the parameters specific to the tool specified in toolName. Refer to the individual tool descriptions for the required parameters.

常见问题

6 问
答案由本站依据条目字段整理,不引用上游原文
Image Processing MCP Server 怎么安装?

资料没有给出安装命令,请到官方仓库或文档按说明接入;这类条目多数是生态应用,或尚未发布可安装包。

Image Processing MCP Server 怎么在 Claude、Cursor 里配置?

它的传输方式未标注,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Image Processing MCP Server 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Image Processing MCP Server 需要 API Key 吗?

资料标注为无需认证,装好就能连;如果实际调用时报鉴权错误,按官方文档补上凭据。

Image Processing MCP Server 支持哪些客户端?

资料标注支持 Claude、Cursor;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Image Processing MCP Server 能提供哪些能力?

资料显示约 6 个工具;能力标签包括 图像处理、格式转换、TypeScript、Claude、批量操作。具体工具清单以官方文档为准。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。