EditX
An MCP server for taking screenshots and editing images with annotations, shapes, and effects.
README
EditX - Screenshot & Image Editor MCP Server
MCP server for taking screenshots and editing images with annotations, shapes, and effects. Inspired by ShareX functionality for Linux.
Features
📸 Screenshot Capture
- Fullscreen: Capture entire screen
- Area Selection: Interactive region selection (GUI)
- Region: Capture specific coordinates programmatically
✏️ Drawing Tools
- Arrows: Point to specific areas
- Rectangles: Highlight regions
- Step Numbers: Numbered circles for tutorials (1, 2, 3...)
- Text: Add text annotations
🎨 Effects
- Blur: Gaussian blur for privacy
- Pixelate: Stronger privacy effect (faces, sensitive data)
- Crop: Cut image to specific region
💾 Image Management
- Load existing images
- Save in PNG/JPEG
- Undo operations
- Reset to original
- Image info and history
Installation
cd /path/to/EditX
pip install -r requirements.txt
System Dependencies (Linux)
For interactive area selection, install one of:
# Ubuntu/Debian
sudo apt install gnome-screenshot
# OR
sudo apt install scrot
Configuration
Add to ~/.claude.json:
{
"mcpServers": {
"editx": {
"type": "stdio",
"command": "python",
"args": [
"/absolute/path/to/EditX/src/server.py"
]
}
}
}
Replace /absolute/path/to/EditX with the actual path where you cloned this repository.
Usage Examples
Basic Workflow
1. Take screenshot
→ take_screenshot(mode="fullscreen")
2. Add annotations
→ add_arrow(start_x=100, start_y=100, end_x=200, end_y=150)
→ add_rectangle(x=150, y=150, width=300, height=200)
→ add_step_number(x=250, y=250, number=1)
3. Add privacy blur
→ blur_region(x=400, y=100, width=200, height=50)
4. Save result
→ save_image(output_path="/path/to/annotated.png")
Tutorial Screenshot with Steps
take_screenshot(mode="area")
add_step_number(x=100, y=100, number=1, bg_color="red")
add_step_number(x=100, y=200, number=2, bg_color="blue")
add_step_number(x=100, y=300, number=3, bg_color="green")
add_arrow(start_x=150, start_y=100, end_x=300, end_y=100)
save_image(output_path="tutorial.png")
Privacy Screenshot
take_screenshot(mode="fullscreen")
blur_region(x=100, y=100, width=300, height=200, blur_amount=20)
pixelate_region(x=500, y=500, width=200, height=200, pixel_size=15)
save_image(output_path="private.png")
Edit Existing Image
load_image(image_path="/path/to/existing.png")
add_rectangle(x=50, y=50, width=400, height=300, color="red", border_width=5)
add_text(x=60, y=60, text="Important!", color="red", size=24, bg_color="white")
save_image(output_path="/path/to/annotated.png")
Available Tools
Screenshot Tools
take_screenshot: Capture screenmode: "fullscreen" | "area" | "region"output_path: (optional) where to savex, y, width, height: (for "region" mode)
Editing Tools
-
load_image: Load existing image fileimage_path: path to image
-
add_arrow: Draw arrowstart_x, start_y: arrow startend_x, end_y: arrowhead positioncolor: arrow colorwidth: line width
-
add_rectangle: Draw rectanglex, y: top-left cornerwidth, height: dimensionscolor: border colorborder_width: border thicknessfill: (optional) fill color
-
add_step_number: Add numbered circlex, y: center positionnumber: step number (1, 2, 3...)size: circle diameterbg_color: circle colortext_color: number color
-
add_text: Add text annotationx, y: text positiontext: text contentcolor: text colorsize: font sizebg_color: (optional) background
Effects
-
blur_region: Blur specific areax, y, width, height: regionblur_amount: intensity (5-50)
-
pixelate_region: Pixelate area (privacy)x, y, width, height: regionpixel_size: block size (5-30)
-
crop_image: Crop to regionx, y, width, height: crop area
Management
-
save_image: Save edited imageoutput_path: where to saveformat: "PNG" | "JPEG"
-
get_image_info: Get image details -
undo: Undo last operation -
reset_image: Reset to original
Technical Details
Architecture
EditX/
├── src/
│ ├── server.py # MCP server (main entry)
│ ├── screenshot.py # Screenshot capture (mss)
│ ├── editor.py # Image editor manager
│ ├── shapes.py # Drawing shapes (Pillow)
│ └── effects.py # Image effects (Pillow + OpenCV)
├── requirements.txt
└── README.md
Technology Stack
- MCP Framework: Server implementation
- python-mss: Fast cross-platform screenshots
- Pillow (PIL): Image manipulation and drawing
- OpenCV: Advanced effects (blur, pixelate)
- NumPy: Array operations
Workflow
- Screenshot is captured and auto-loaded into editor
- All edits are applied to the loaded image
- Editor maintains history (up to 10 states)
- Undo/reset available at any time
- Save to desired format
Colors Available
red,blue,green,yellow,black,white,orange
Tips
- Step numbers: Use different colors for different workflows
- Blur vs Pixelate: Blur for slight privacy, pixelate for strong privacy
- Arrow direction: Arrow points to
endcoordinates - History: Max 10 undo states kept in memory
- Formats: Use PNG for transparency, JPEG for smaller files
License
MIT License - see LICENSE file for details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。