Advertise
MCP.so
Sign In

Screenshot Server MCP Server

@KunihiroS

Repository

Basic information

Category

Browser Automation

Transports

stdio

Author

KunihiroS

Submitted by

Kunihiro Sugiyama

About Screenshot Server MCP Server

MCP Server for local screen shot.

#screenshot#mcp-server#image-capture

Screenshot Server MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Screenshot-server": {
      "command": "powershell.exe",
      "args": [
        "-Command",
        "Invoke-Command -ScriptBlock { cd '<YOUR_WINDOWS_PROJECT_PATH>'; & '<YOUR_WINDOWS_UV_PATH>' run screenshot.py }"
      ]
    }
  }
}

Screenshot Server MCP Server tools

7

** Takes a screenshot, converts the provided WSL path to a UNC path, and saves the file to the Host's workspace. Automatically detects the WSL distribution name.

`host_workspace_path` (str): The absolute WSL path of the Host's workspace (e.g., `/home/user/project`).

** `str` - `"success"` or `"failed: [error message]"`.

`name` (str, optional): Filename. Defaults to `latest_screenshot.jpg`.

** `str` - Absolute path or `"failed: [error message]"`.

`path` (str, optional): Target directory (Windows or UNC path). Defaults to server's working directory.

** `str` - `"success"` or `"failed: [error message]"`.

Overview

What is Screenshot Server?

Screenshot Server is an MCP (Modular Communication Protocol) server that captures screenshots and saves them to a file path specified by the client, enabling AI assistants or other processes to access the screenshot via its file path.

How to use Screenshot Server?

Deploy the server on Windows (required for capturing the Windows screen), install dependencies with uv sync, and configure the MCP host to launch it (e.g., via PowerShell in WSL). Use the provided tools: save_screenshot_to_host_workspace, take_screenshot_and_return_path, or take_screenshot_path.

Key features of Screenshot Server

  • Captures the entire Windows screen.
  • Saves screenshots to a file path specified by the client.
  • Converts WSL paths to Windows UNC paths automatically.
  • Provides three tools with different save destinations.
  • Logs server activity to server.log.

Use cases of Screenshot Server

  • An AI assistant in WSL captures a screenshot and saves it directly into its workspace.
  • A process saves a screenshot to a fixed images/ directory and returns the absolute path.
  • A user saves a screenshot to an arbitrary Windows or UNC path for external processing.

Frequently asked questions

1

What is the recommended workflow for WSL2?

The recommended workflow uses `save_screenshot_to_host_workspace` with WSL workspace path; the server converts it to a UNC path, saves the screenshot, and returns `"success"`.

2

What tools does Screenshot Server provide?

Three tools: `save_screenshot_to_host_workspace` (recommended), `take_screenshot_and_return_path`, and `take_screenshot_path`.

3

Where does Screenshot Server save screenshots?

It saves to a path specified by the client: either the host’s workspace (via UNC path conversion), a local `images/` directory, or an arbitrary directory given as a Windows or UNC path.

4

What are the runtime requirements?

Python 3.x, dependencies `mcp[cli]>=1.4.1`, `pyautogui`, and `Pillow`, installed via `uv sync`. The server must run directly on Windows to capture the screen.

Comments

More Browser Automation MCP servers

Loadster

loadster

Loadster is a load testing, stress testing, and synthetic monitoring platform. Run Playwright, Browser Bots, and Protocol Bots to test and monitor your websites, web apps, and APIs. Loadster MCP gives your agents the abi

playwright-server MCP server

blackwhite084

189

HTML/CSS to Image

An MCP server for generating images from HTML & CSS or screenshots of URLs using htmlcsstoimage.com.

Screenshot Scout

screenshotscout

Capture screenshots of webpages as images or PDFs with Screenshot Scout.

Fastcrw

us

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.

286
Advertise