%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Mcpvil
MCPvil is a minimized Wayland compositor based on the smallvil branch of the Smithay project. It integrates an MCP server, allowing AI agents and other MCP clients to interact with the compositor through stdio, providing functions such as application launch, screen capture, and mouse and keyboard simulation.
rating : 2 points
downloads : 4.1K
What is MCPvil?
MCPvil is an innovative desktop control tool that connects the Wayland desktop environment (a graphical interface system similar to Windows or macOS) with an AI assistant. Through the Model Context Protocol (MCP), the AI assistant can operate your computer desktop like a human: launch applications, take screenshots, move the mouse, click buttons, input text, etc.How to use MCPvil?
After installing MCPvil, simply configure MCPvil as a tool in an AI assistant (such as Claude, Gemini, etc.), and the AI can control your desktop through simple dialogue instructions. For example, you can say 'Help me open the browser and visit GitHub', and the AI will automatically perform these operations.Applicable scenarios
Suitable for scenarios that require automated desktop operations: automated testing, remote assistance, automation of repetitive tasks, assisting disabled people in operating computers, teaching demonstrations, etc.Main features
Application control
The AI can launch and close any application on the desktop, just like you operate in the terminal or start menu.
Intelligent screenshot
The AI can take a screenshot of the desktop at any time, save it as an image file or directly obtain the image data for analysis or recording.
Mouse operation
The AI can precisely control the mouse movement, click, and scroll, simulating human mouse operations.
Keyboard input
The AI can simulate keyboard buttons to input text or shortcuts, realizing automated input operations.
Visualization window
You can open an independent GUI window to view and control the desktop status in real - time.
MCP protocol support
It uses the standard Model Context Protocol and is compatible with various AI assistant platforms such as Claude and Gemini.
Advantages
No programming knowledge required: You can control desktop operations through natural language.
Cross - platform compatibility: Supports all Linux systems that support Wayland.
AI assistant integration: Seamlessly integrates with mainstream AI assistants.
Open - source and free: Based on an open - source project, it can be freely used and modified.
Comprehensive functions: Covers the main functions of desktop operations.
Limitations
Linux only: Currently only supports Linux systems (Wayland desktop environment).
Requires technical configuration: Installation and configuration require some command - line operation experience.
Depends on system permissions: Requires installing system dependency libraries and permissions.
Real - time limitation: The operation response speed is affected by the AI assistant and the network.
Relatively basic functions: Fewer functions compared to professional automation tools.
How to use
Install system dependencies
Install necessary development libraries and dependency packages on Ubuntu/Debian systems.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%230080ff;%20}%20%3c/style%3e%3c/defs%3e%3cpath%20class='st0'%20d='M16.2,11.1c.4.5.4,1.2,0,1.8l-4.7,7.1h-3.8l5.3-8L7.6,4h3.8l4.7,7.1Z'/%3e%3c/svg%3e)
Install MCPvil
Install MCPvil through the Cargo package manager.
Configure the AI assistant
Add MCPvil as a tool in Claude Code or Gemini CLI.
Start using
Start MCPvil, and then send instructions through the AI assistant to control the desktop.
Usage examples
Automated web browsing
Let the AI automatically open the browser, visit a specific website, and take a screenshot and save it.
Repetitive form filling
Automatically fill in repetitive form data.
Remote assistance demonstration
Demonstrate specific operation steps to others.
Automated testing
Automatically test the startup and basic functions of an application.
Frequently Asked Questions
Does MCPvil support Windows or macOS?
Do I need programming knowledge to use it?
Is MCPvil safe? Will it be maliciously exploited?
Which AI assistants are supported?
What should I do if an operation goes wrong?
Can it control all desktop applications?
Related resources
GitHub repository
The source code and latest version of MCPvil
Smithay project
The Wayland compositor library that MCPvil is based on
Model Context Protocol official website
The official documentation and specifications of the MCP protocol
Wayland protocol documentation
Documentation for the Wayland display server protocol
Rust programming language
The programming language used by MCPvil
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.4K
5 points
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.2K
4.3 points
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.6K
4.3 points
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.2K
5 points
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.5K
4.5 points
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.1K
4.5 points
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
47.8K
4.8 points