Contains computer control and automation components for MCP servers

Showcasing the integration of computer vision tools with language models through MCP

MCP-DBLP is a service based on the Model Context Protocol (MCP) that provides large language models with the ability to access the DBLP computer science literature database, including functions such as search, citation processing, and BibTeX export.

A TypeScript - based MCP server for file system editing tools, ported from the Anthropic computer usage demonstration.

An OpenAI agent server based on the MCP protocol, providing various professional agents (such as web search, file search, and computer operation) and a multi-agent coordinator, which can interact with clients (such as the Claude desktop application) through the MCP protocol.

A computer vision server implemented based on Ultralytics and the MCP protocol, supporting functions such as object detection, image segmentation, and pose estimation

An MCP server based on computer vision that automatically identifies the positions of image assets and extracts the layout structure by analyzing web page screenshots, supports the detection of multiple layout patterns such as radial and grid, and helps AI assistants accurately reconstruct web page layouts.

A server based on the MCP protocol, providing the function of querying the prices of computer components on the CoolPC website in Taiwan and automatically generating computer configuration quotes.

An MCP server that provides information about the installed applications on a computer, supporting MacOS and Windows systems, and can be integrated with compatible AI assistants.

An MCP server for seamless integration with computer peripherals, providing a unified API to control, monitor, and manage hardware devices, including cameras, printers, audio devices, and screens.

The YOLO MCP Service is a powerful computer vision service that integrates with Claude AI through the Model Context Protocol (MCP), providing functions such as object detection, segmentation, classification, and real-time camera analysis.

A privacy - first document search server that runs entirely locally, providing semantic search functions for AI programming tools through the MCP protocol. No API keys or cloud services are required, and all data processing is completed on the user's computer.

Computer control and automation components of the MCP server

Desktop Commander MCP is a service that enables the Claude desktop application to execute terminal commands on the user's computer and manage processes through the Model Context Protocol (MCP). It provides terminal command execution, process management, file system operations, and code editing functions, supporting long-running commands and differential file editing.

A TypeScript-based MCP server for interacting with DAOs on the Internet Computer

This is an MCP server designed for the Commodore 64 Ultimate (the official modern C64 computer). It allows AI assistants (such as Claude, ChatGPT) to remotely control C64 hardware through a REST API, supporting functions such as program loading, memory operations, and disk management.

An MCP service that allows Claude to control audio playback on the computer

An MCP server that provides computer control functions, including mouse and keyboard control, OCR recognition, window management, etc., implemented based on PyAutoGUI and RapidOCR without external dependencies.

An MCP server based on nut.js that provides comprehensive control functions for the computer screen, mouse, and keyboard, including screenshot, mouse operation, keyboard input, window management, and clipboard access.

Koppla is a natural language-based Active Directory management tool that enables querying and operating on user, group, and computer objects through an AI agent.

Android-MCP is a lightweight open-source project that serves as a bridge between AI agents and Android devices. It enables real-world task operations such as app navigation, UI interaction, and automated testing through the MCP server, without relying on traditional computer vision or pre-set scripts.

Claude Desktop Commander MCP is a server tool that allows the Claude desktop application to execute terminal commands and manage processes on the user's computer. It is built based on the Model Context Protocol (MCP) and provides file system operations and code editing functions.

MCP Hub is a framework for creating and managing Model Context Protocol (MCP) servers and clients, integrating the UV tool to simplify package management and configuration. The project includes AI - related computer vision scripts and dataset processing tools, supporting rapid deployment and development.

The OpenCV MCP Server is a Python - based computer vision service that provides OpenCV's image and video processing capabilities through the Model Context Protocol (MCP). It offers a full set of computer vision tools from basic image processing to advanced object detection for AI assistants and language models, including image processing, edge detection, face recognition, video analysis, and real - time object tracking.

An MCP server that provides computer control functions, including mouse and keyboard control, screen capture, OCR text recognition, etc. It supports cross - platform operation and requires no external dependencies.

termiAgent is an LLM-based command-line assistant that supports plugin role settings and MCP server connection, aiming to simplify computer operations.

An MCP server that provides audio input/output functions, supporting the interaction between AI assistants like Claude and the computer's audio system, including functions such as recording and playing audio files.

Create a directory website for MCP servers and share Claude code tips and creative computer applications

The notify-completion-mcp-server is an MCP server that sends notifications when an AI agent completes a long-running task, helping users know the task completion status without constantly monitoring their computers.

Serial-MCP is a serial communication server based on the FastMCP framework, providing functions such as asynchronous serial communication, message buffering, connection management, and error handling. It supports parameter configuration through environment variables and is suitable for reliable data exchange between devices and computers.

The AI MCP server is a bridge connecting AI models and computer systems, supporting system command execution, file operations, program control, and inter - model communication. It provides automated installation and the ability to integrate multiple AI models.

Overlord is an AI management project that controls macOS through the local computer, providing direct system control and support for multiple LLM providers.

This is a FiftyOne MCP server project that allows users to use natural language through AI assistants (such as ChatGPT and Claude) to explore and manage computer vision datasets. It provides functions such as dataset management, operation execution, plugin installation, and session control, exposing more than 80 built - in operators and the plugin ecosystem of FiftyOne to AI tools.

The Computer Use AI SDK developed by Screenpipe is an open - source project that provides an MCP server and client for controlling computer operations through AI. It supports the native macOS environment, does not require a virtual machine, can directly interact with any application or website, and provides basic functions such as launching applications, reading content, clicking, and entering text, aiming to build automated workflows and intelligent agents.

An MCP service that enables programmatic control of the computer screen, mouse, and keyboard through nut.js, providing automation operation functions such as screenshot, input simulation, and window management

The Data MCP Server is a toolset that provides web page scraping, structured data extraction, and crawling functions, and also supports multiple browser proxy tools such as OpenAI CUA and Claude Computer Use.

DigitalFate is an enterprise-level LLM task orchestration framework that supports multi-level task processing, tool integration, and computer operations.

DigitalFate is an enterprise-level framework for efficiently coordinating LLM calls, intelligent agents, and computer tasks, providing scalable production environment deployment, task-oriented architecture, and multi-client processing capabilities.

A server based on the MCP protocol for obtaining the list of installed applications on a computer, supporting MacOS and Windows systems.

Upsonic is a reliability - focused framework aiming to achieve trustworthy agent workflows within an organization through advanced reliability features such as a validation layer, triangular architecture, validation agents, and an output evaluation system. It addresses key challenges such as reliability, Model Context Protocol (MCP), integrated browser and computer usage, and secure runtime.