screenshot-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., "@screenshot-mcp take a screenshot of my desktop and describe what you see"
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.
📸 screenshot-mcp
给 AI 装上一双眼睛 — 让 Claude Code 能截图、看图、自动清理的 MCP 服务器
这是什么?
screenshot-mcp 是一个 MCP (Model Context Protocol) 服务器,让 AI 助手(如 Claude Code)可以直接在你的 Windows 桌面上:
能力 | 说明 |
📷 截图 | 全屏截图、区域截图、活动窗口截图 |
👁️ 看图 | 读取图片让 AI 视觉分析 |
🗑️ 自动删图 | 按条件清理旧截图,用完即走 |
工作原理
┌──────────────────────┐ MCP 协议 ┌──────────────────────┐
│ │◄──────────────────────►│ │
│ Claude Code │ tools/list │ screenshot-mcp │
│ (MCP 客户端) │ tools/call │ (MCP 服务器) │
│ │ │ │
│ "帮我看看桌面" ──────┼── screenshot ──────────►│ PowerShell .NET │
│ "这个界面怎么样" ─────┼── screenshot_region ────►│ System.Drawing │
│ "把截图删掉" ────────┼── cleanup ──────────────►│ fs.unlinkSync │
└──────────────────────┘ └──────────────────────┘
│
┌────────────┴────────────┐
│ Windows 原生截图 API │
│ (无需额外工具) │
└─────────────────────────┘Related MCP server: screen-capture-mcp
快速开始
前置要求
Windows 10/11(截图依赖 Windows GDI+)
Node.js 18 或更高版本
Claude Code(或其他 MCP 客户端)
安装
# 1. 克隆仓库
git clone https://github.com/你的用户名/screenshot-mcp.git
cd screenshot-mcp
# 2. 安装依赖
npm install配置(选一种即可)
方式一:全局配置(推荐,所有项目生效)
编辑 ~/.claude.json(在 C:\Users\你的用户名\.claude.json),在 mcpServers 里添加:
"mcpServers": {
"playwright": {
"type": "stdio",
"command": "npx",
"args": ["@playwright/mcp", "--headless"],
"env": {}
},
"screenshot-mcp": {
"command": "node",
"args": ["C:\\你的路径\\screenshot-mcp\\src\\index.js"]
}
}路径说明:
args中的路径要改成你电脑上的实际路径,例如:
项目在桌面:
C:\Users\你的用户名\Desktop\screenshot-mcp\src\index.js项目在 D 盘:
D:\projects\screenshot-mcp\src\index.js
方式二:项目级配置(仅当前项目生效)
在项目目录下创建 .claude/settings.json:
{
"mcpServers": {
"screenshot-mcp": {
"command": "node",
"args": ["C:\\你的路径\\screenshot-mcp\\src\\index.js"]
}
}
}方式三:.mcp.json 文件(自动发现)
在工作目录下创建 .mcp.json,Claude Code 会自动发现并加载:
{
"mcpServers": {
"screenshot-mcp": {
"command": "node",
"args": ["C:\\你的路径\\screenshot-mcp\\src\\index.js"]
}
}
}验证配置是否生效
重启 Claude Code 后,随便说一句:
"你能用 screenshot-mcp 吗?"
如果配置正确,Claude 会回答"可以"并调用截图工具。
使用
配置好后,在 Claude Code 中直接说:
🗣️ "帮我截个图看看桌面" 🗣️ "截取当前活动窗口" 🗣️ "看看这张图片" 🗣️ "把刚才的截图删掉" 🗣️ "清理超过1小时的截图"
提供的工具
工具 | 说明 | 参数 |
| 全屏截图 |
|
| 区域/活动窗口截图 |
|
| 读取图片给 AI 分析 |
|
| 列出所有截图 |
|
| 删除指定图片 |
|
| 批量清理截图 |
|
使用示例
截图 + AI 分析
你:帮我截个图,看看我桌面上有什么
Claude:(调用 screenshot 截图)
(调用 view_image 看图)
→ 你桌面上有这些文件和文件夹……截图指定区域
你:截取当前活动窗口
Claude:(调用 screenshot_region region="active_window")
→ 这是当前窗口的内容……看完自动清理
你:把刚才的截图删掉
Claude:(调用 delete_image 删除指定文件)
→ 已删除安全性
措施 | 说明 |
🛡️ 目录限制 |
|
📦 文件大小限制 | 图片最大支持 20MB |
🔒 本地存储 | 截图保存在本地 |
🧹 自动清理 | 支持按时间批量清理,用完即删 |
技术栈
技术 | 用途 |
运行环境 | |
MCP 协议实现 | |
PowerShell .NET (System.Drawing) | Windows 原生截图 |
JSON-RPC 2.0 | 通信协议 |
纯 Windows 原生实现,无需任何第三方截图工具。
在 GitHub 上使用
如果你把这个项目放在 GitHub 上,别人克隆后会得到一份不带配置的源码。他们需要:
运行
npm install安装依赖在自己的 Claude Code 配置中注册这个 MCP 服务器
把
args中的路径改成自己机器上的实际路径
开源协议
MIT — 随便用,随便改,随便玩。
相关资源
screenshot-mcp — 给 AI 装上一双眼睛 👀
Available Tools
6 toolscleanupA
Delete screenshots. Default: deletes all. Can filter by age or filename pattern.
Inputs: pattern, older_than_hours.
delete_imageA
Delete a specific image file by path.
Inputs: path (required).
list_imagesA
List all screenshot images in the screenshots directory, sorted by newest first.
Inputs: limit.
screenshotA
Take a screenshot of the entire screen. Saves to local screenshots/ directory.
Inputs: filename.
screenshot_regionB
Take a screenshot of a specific screen region. Specify coordinates or use 'active_window'.
Inputs: region, filename.
view_imageA
Read an image file and return it for AI vision analysis. Supports PNG, JPG, GIF, BMP, WEBP.
Inputs: path (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: full-screen capture, region capture, image viewing for vision, listing, specific deletion, and bulk cleanup. The only potential overlap is delete_image and cleanup, but cleanup is clearly bulk with filters, so boundaries are clear.
Most tools follow a verb_noun pattern (view_image, list_images, delete_image), but screenshot, screenshot_region, and cleanup deviate slightly. The naming is still readable and predictable, with only minor inconsistencies.
Six tools is well-scoped for a screenshot server, covering capture, viewing, listing, and deletion without unnecessary bloat. The count feels natural and each tool earns its place.
The server covers the full screenshot lifecycle: capture (full and region), view for AI analysis, list, delete specific, and cleanup. No obvious missing operations are apparent for the stated purpose.
Maintenance
Related MCP Connectors
Hosted Screenshots MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
MCP server for Qwen Image 3 AI image generation
Screenshots, PDFs, image editing, QR codes, email validation and more through one hosted MCP server.
MCP server exposing the YourImageShare upload API (upload/list/delete) as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server for capturing screen regions directly into Claude Code conversations via hotkeys or tool calls. It provides Windows-specific screen snipping with multi-monitor support, persistent storage, and automatic management of captured images.MIT
- AlicenseAqualityDmaintenanceAn MCP server that enables Claude Code and other MCP clients to take screenshots of the full screen or specific windows, with support for repeated captures over intervals.136 npm8MIT
- AlicenseNot gradedqualityBmaintenanceOpen-source screenshot tool for Windows with a built-in MCP server that allows AI assistants like Claude to capture and view screen content through tools like take_screenshot, ask_user_to_select_region, and more.3MIT
- AlicenseNot gradedqualityDmaintenanceA Windows MCP server that enables AI agents to capture screenshots of open windows or the full desktop via stdio or HTTP.MIT