local-only server
The server can only run on the client’s local machine because it depends on local resources.
Integrations
Enables browser automation through Playwright, allowing navigation, DOM interaction, element selection, and JavaScript execution in Chrome
Supports executing JavaScript within Chrome browser contexts for enhanced web page interaction and manipulation
Required as a runtime dependency for the server's browser automation capabilities
If you are looking for the MCP server: find it here.
If you are looking for the Python Library, go on.. ;)
Smooth Operator Agent Tools - Python Library
This is the official Python library implementation for Smooth Operator Agent Tools, a state-of-the-art toolkit for programmers developing Computer Use Agents on Windows systems.
Overview
The Smooth Operator Agent Tools are a powerful toolkit that handles the complex tasks of interacting with the Windows Automation Tree and Playwright browser control, while providing advanced AI functions such as identifying UI elements through screenshots and textual descriptions.
This Python library provides a convenient wrapper around the Smooth Operator Tools Server API, allowing you to easily integrate these capabilities into your Python applications.
All features can be tested and explored through a convenient Windows user interface before implementing them in code. Try them out at Smooth Operator Tools UI.
Installation
Prerequisites
Google Chrome
The Smooth Operator Agent Tools library requires Google Chrome (or a compatible Chromium-based browser) to be installed on the system for browser automation features to work.
Server Installation
The Smooth Operator client library includes a server component that needs to be installed in your application data directory. The server files are packaged with the library and will be automatically extracted on first use.
First-Time Execution
When you first use the library, it will automatically:
- Create the directory
%APPDATA%\SmoothOperator\AgentToolsServer
(or the equivalent on your OS) - Extract the server files from the package
- Start the server process
Note that for Chrome automation features to work, you need to ensure Node.js and Playwright are installed as described in the Prerequisites section.
For Application Installers
If you're building an application installer that includes this library, you should include steps to install Node.js and Playwright during your application's installation process for better user experience. See the Prerequisites section for the required installation steps.
Usage
Features
- Screenshot and Analysis: Capture screenshots and analyze UI elements
- Mouse Control: Precise mouse operations using coordinates or AI-powered element detection
- Keyboard Input: Type text and send key combinations
- Chrome Browser Control: Navigate, interact with elements, and execute JavaScript
- Windows Automation: Interact with Windows applications and UI elements
- System Operations: Open applications and manage system state
Documentation
For detailed API documentation, visit:
- Usage Guide: Detailed examples and explanations for common use cases.
- Example Project: Download, follow step by step instructions and have your first automation running in mintes.
- Documentation: Detailed documentation of all the API endpoints of the server that is doing the work internally.
License
This project is licensed under the MIT License - see the LICENSE file for details.
This server cannot be installed
Windows automation MCP offering
- AI Vision (e.g. Click by Description)
- Windows UI Automation Tree tools
- Chrome Automation via Playwright
- Mouse control
- Keyboard control
- a lot more (>40 tools)
Also comes with Python/TypeScript/C# client libs and a Windows Desktop tool to try all the tools.