Windows Driver Input MCP
An independent MCP server that provides driver-level keyboard and mouse input control tools through IbInputSimulator, supporting operations such as text input, shortcuts, and window management, without requiring UIA or visual modules.
rating : 2 points
downloads : 6.2K
What is the Windows Driver Input MCP Server?
This is an input simulation MCP server specifically designed for the Windows system. It directly controls the keyboard and mouse through driver-level technology, rather than through UI automation or the operating system Shell. This means it can bypass the security restrictions of some applications and achieve more reliable and efficient input simulation.How to use the Windows Driver Input MCP Server?
You need to install the necessary dependencies (Python 3.13+ and the UV package manager) first, and then configure and start the server through supported AI clients (such as Claude Desktop, Codex CLI, Gemini CLI). After the configuration is complete, the AI assistant can control your computer to perform various input operations through this server.Applicable scenarios
Suitable for scenarios that require automated Windows desktop operations, such as game automation, software testing, repetitive task automation, assistive function tools, remote control assistance, etc. Particularly suitable for applications that need to bypass UI automation restrictions or require high-performance input simulation.Main features
Driver-level input
Achieve driver-level keyboard and mouse input simulation through the IbInputSimulator library, bypassing the security restrictions of applications and providing more reliable input control.
Multiple input methods
Support multiple input operations such as Unicode text input, keyboard shortcuts, key combinations, mouse movement, clicking, dragging, and scrolling.
Dual backend support
Provide two backend implementations: ibsim-dll (no need for AutoHotkey) and ibsim-ahk (requires AutoHotkey v2 64-bit). Users can choose according to their needs.
Window management
Support window management operations such as getting window information, enumerating the window list, activating windows, adjusting window position and size.
Rate control
Configure parameters such as mouse movement frequency, maximum movement increment, smoothness, character input speed, and key press speed to achieve fine-grained input control.
Multi-client support
Support multiple AI clients such as Claude Desktop, Codex CLI, Gemini CLI, and provide corresponding configuration examples.
Advantages
Driver-level input, bypassing application security restrictions
No need for UI automation or the Shell, reducing dependencies
Support Unicode text input, suitable for multilingual environments
Provide fine-grained rate control parameters
Open-source project under the MIT license, can be freely used and modified
Support configuration of multiple AI clients
Limitations
Only support Windows 7 - 11 operating systems
Require Python 3.13+ and the UV package manager
Some functions require administrator privileges
The ibsim-ahk backend requires the installation of AutoHotkey v2 64-bit
Do not provide visual recognition or UI element positioning functions
How to use
Environment preparation
Ensure that your system is Windows 7 - 11, and install Python 3.13+ and the UV package manager (can be installed via pip install uv).
Clone the repository
Clone the project from GitHub to a local directory.
Configure the AI client
According to the AI client you are using (Claude Desktop, Codex CLI, or Gemini CLI), configure it according to the JSON configuration example in the documentation.
Start the server
The server supports two transmission methods: stdio (standard input/output) and SSE (Server-Sent Events).
Start using
After the configuration is complete, you can use various input tools through the AI assistant, such as moving the mouse, clicking, and inputting text.
Usage examples
Automated text input
Automatically input multiple lines of text in Notepad or other text editors
File operation automation
Automatically perform file copying, renaming, and other operations
Window management
Organize and arrange multiple application windows
Game assistance
Perform repetitive operations in the game
Frequently Asked Questions
Does this server require administrator privileges?
What is the difference between the ibsim-dll and ibsim-ahk backends?
How to adjust the input speed?
Which Windows versions does the server support?
Will the input operations be blocked by the antivirus software?
How to debug input issues?
Related resources
GitHub repository
Project source code and latest documentation
IbInputSimulator project
Technical documentation of the underlying input simulation library
Windows-MCP project
Reference implementation of related functions
UV package manager
Python package manager and installation tool
AutoHotkey v2
Automation scripting language (required for the ibsim-ahk backend)
Model Context Protocol
Official specification of the MCP protocol

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
17.8K
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
28.3K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
56.8K
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
18.1K
4.3 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
52.3K
4.5 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#
25.1K
5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
78.3K
4.7 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
37.7K
4.8 points

