Screenshot

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

python

24

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "codingthefuturewithai-screenshot_mcp_server": {
      "command": "screenshot_mcp_server-server",
      "args": []
    }
  }
}

The Screenshot MCP Server provides AI tools with the ability to capture and process screen content by delivering full-screen JPEG screenshots through MCP transport. It handles image capture, compression, and transmission in a format suitable for AI processing, enabling seamless visual context for assistants.

How to use

You can use the server with an MCP client to request a screenshot and receive a base64-encoded JPEG image that you can feed into your AI processing pipeline. There are two primary usage patterns: a local, command-line workflow via stdio and a programmatic workflow via a client session.

From a command line: run a local MCP client that talks to the stdio server and request a screenshot.
Programmatically: connect through a stdio-based client to call the take_screenshot tool and process the returned image data in your application.

How to install

Prerequisites you need before install: Python 3.10 or later (3.10–3.12 are supported). You also need a Python package manager and an MCP client runtime.

# Clone the server repository
git clone https://github.com/codingthefuturewithai/screenshot_mcp_server.git
cd screenshot_mcp_server

# Install the MCP server in editable mode using UV
uv pip install -e .

# Alternatively, install with pip directly
pip install -e .

To run the SSE (web-based) transport endpoint, start the server on port 3001. This enables web-based applications to connect via MCP with SSE transport.

screenshot_mcp_server-server-sse --port 3001

Examples and basic usage

Take a screenshot from the command-line client and save it to a file, or use the programmatic path to integrate into your tooling.

# Command-line client example
screenshot_mcp_server-client output.jpg

Programmatic usage shows how to call the take_screenshot tool via an MCP stdio client in your Python application. This lets you process the resulting JPEG image data within your AI workflow.

Available tools

take_screenshot

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