为 AI 工具提供截图功能的 MCP 服务器，允许其捕获和处理屏幕内容。
这款 MCP 服务器使 AI 工具能够截取用户的屏幕截图，从而使 AI 助手能够查看并分析用户正在查看的内容。该服务器负责图像的捕获、压缩，并以适合 AI 处理的格式进行传输。
Related MCP server: Shotik
截取全屏截图
自动 JPEG 压缩，实现高效传输
Base64 编码图像数据以实现可靠传输
支持 stdio 和 SSE 传输模式
可配置的图像质量和优化
用于测试的简单命令行界面
# Clone the repository
git clone https://github.com/codingthefuturewithai/screenshot_mcp_server.git
cd screenshot_mcp_server
# Install using UV (recommended)
uv pip install -e .
# Or using pip
pip install -e .描述：截取用户屏幕的屏幕截图并将其作为 JPEG 图像返回。
参数：无
返回：
JPEG 格式的图像内容，base64 编码
该服务器可以以两种方式使用：
# Take a screenshot and save it to a file
screenshot_mcp_server-client output.jpgfrom mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
async with stdio_client(StdioServerParameters(command="screenshot_mcp_server-server")) as (read, write):
async with ClientSession(read, write) as session:
result = await session.call_tool("take_screenshot")
# Process the screenshot data...Python 3.10 或更高版本（<3.13）
依赖项：
mcp >= 1.0.0
pyautogui >= 0.9.54
枕头> = 10.0.0
操作系统：Linux、macOS、Windows
服务器支持两种传输模式：
stdio（默认）：用于命令行使用
SSE：适用于基于 Web 的应用程序，默认在端口 3001 上运行
要在 SSE 模式下运行：
screenshot_mcp_server-server-sse --port 3001该项目已获得 MIT 许可。
蒂姆·基钦斯（ timkitch@codingthefuture.ai ）
Take a screenshot of the user's screen and return it as an image
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states the action and output format but lacks details on behavioral traits such as permissions required, whether it captures the entire screen or a region, privacy implications, or error handling. This is a significant gap for a tool with potential security and usability concerns.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core action and outcome with zero wasted words. It is appropriately sized for the tool's simplicity and directly communicates its purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (a potentially sensitive screen capture tool) and lack of annotations or output schema, the description is incomplete. It fails to address critical context like security permissions, scope of capture, or return format details, leaving gaps that could hinder safe and effective use by an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description does not add parameter semantics, but this is acceptable as there are no parameters to explain, aligning with the baseline for zero parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('take a screenshot') and the resource ('user's screen'), with the outcome specified ('return it as an image'). It distinguishes this tool's purpose unambiguously, especially given no sibling tools exist for comparison.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context (e.g., when a visual capture of the screen is needed) but does not provide explicit guidance on when to use it versus alternatives or any exclusions. With no sibling tools, this is adequate but lacks depth on prerequisites or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
take_screenshotScored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'take_screenshot' has a clearly distinct and unambiguous purpose.
The naming follows a consistent verb_noun pattern with 'take_screenshot'. Since there is only one tool, there is no inconsistency or deviation from any pattern.
A single tool for a screenshot server is too minimal for typical use cases. While it directly serves the core function, it lacks supporting tools (e.g., for selecting regions, managing screenshots, or configuring settings), making it feel thin and incomplete for the domain.
The tool surface is severely incomplete for a screenshot domain. It only provides a basic capture function, with no tools for editing, saving, annotating, or managing screenshots, which are common in such applications, leading to significant gaps in functionality.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.
Grabbit gives AI agents eyes on the web through a hosted MCP server. Send a public URL and get a pixel-perfect hosted image back, without maintaining Chromium, Playwright, or a browser fleet. Capture a full page, exact viewport, or single CSS selector as PNG, JPEG, or WebP. Grabbit handles cookie and consent banners, waits for JavaScript-heavy pages, blocks private and internal URLs, supports safe retries with idempotency keys, and delivers async results through signed webhooks. Completed captures include a CDN URL. Connect with OAuth 2.1 or an API key. Grabbit works with Claude, Cursor, Codex, and any MCP client. Live captures cost $0.002 each. The $50 annual plan includes 25,000 prepaid credits that never reset or expire. Free test keys return placeholder images, so you can wire up the integration before paying. Home: https://grabbit.live Docs: https://grabbit.live/screenshot-api Built by BrainGrid.
