mcpField
S
Screenshot MCP Server

Screenshot MCP Server

Local
github.com/codingthefuturewithaiBrowser Automation26Updated 86w ago
Repository

About Screenshot MCP Server

Screenshot MCP Server is an MCP server that gives AI tools the ability to capture and process screen content. It returns screenshots as base64-encoded JPEG images suited for AI processing.

Key features

  1. 01Full screen capture
  2. 02Automatic JPEG compression
  3. 03Base64 encoded image data
  4. 04stdio and SSE transport modes
  5. 05Configurable image quality
  6. 06Command-line test client

Use cases

  1. 01Letting an AI assistant see what the user is viewing
  2. 02Providing screenshots for AI analysis of interfaces
  3. 03Saving screen captures to a file from the command line

MCP support

The server exposes a take_screenshot tool to MCP clients, returning the screen capture as a base64-encoded JPEG image.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Screenshot MCP Server

An MCP server that provides screenshot capabilities for AI tools, allowing them to capture and process screen content.

Overview

This MCP server enables AI tools to take screenshots of the user's screen, making it possible for AI assistants to see and analyze what the user is looking at. The server handles image capture, compression, and delivery in a format suitable for AI processing.

Features

  • Take full screen screenshots
  • Automatic JPEG compression for efficient transfer
  • Base64 encoded image data for reliable transmission
  • Support for both stdio and SSE transport modes
  • Configurable image quality and optimization
  • Simple command-line interface for testing

Installation

From Source
# 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 .

Available Tools

take_screenshot

Description: Takes a screenshot of the user's screen and returns it as a JPEG image.

Parameters: None

Returns:

  • Image content in JPEG format, base64 encoded

Usage

The server can be used in two ways:

Command Line Client
# Take a screenshot and save it to a file
screenshot_mcp_server-client output.jpg
Programmatic Usage
from 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...

Requirements

  • Python 3.10 or later (< 3.13)
  • Dependencies:
    • mcp >= 1.0.0
    • pyautogui >= 0.9.54
    • Pillow >= 10.0.0
  • Operating Systems: Linux, macOS, Windows

Configuration

The server supports two transport modes:

  • stdio (default): For command-line usage
  • SSE: For web-based applications, runs on port 3001 by default

To run in SSE mode:

screenshot_mcp_server-server-sse --port 3001

License

This project is licensed under the MIT License.

Author

Tim Kitchens ([email protected])

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.