Control Windows desktop apps through MCP with Terminator

Control Windows desktop apps through MCP with Terminator

Connect Terminator MCP to an agent so it can inspect and automate real Windows desktop and browser workflows with pixels, DOM, and accessibility context.

Prerequisites

MCP-capable client such as Claude Code, Cursor, or VS Code, Node.js/npx, Terminator MCP agent package, Windows desktop environment for full native automation

Installation

Requirements and caveats from upstream:

• | Python (terminator.py) | Partial | No | No | pip install terminator |

Basic usage or getting-started notes:

• 08/25 Big release — NodeJS SDK in YAML workflows, run JS in browser, OS event recording → YAML generation in MCP, and more

• Usage: Open the app you want to inspect → launch Accessibility Insights → hover or use keyboard navigation to explore the UI tree (Name, Role, ControlType, AutomationId).

• Source: https://github.com/mediar-ai/terminator

• Extracted from upstream docs: https://raw.githubusercontent.com/mediar-ai/terminator/HEAD/README.md

Documentation

• https://github.com/mediar-ai/terminator/tree/main/terminator-mcp-agent

Source

• Agent Skill Exchange