# AI Agent

PyMCPAutoGUI is a tool that provides graphical user interface (GUI) automation capabilities for AI agents through the MCP protocol. It supports mouse and keyboard control, screenshot, window management, etc., and can be seamlessly integrated into MCP-compatible environments such as the Cursor editor.

An MCP server based on browser-use that allows AI agents to control web browsers via the SSE or stdio protocol, supporting real-time VNC monitoring and asynchronous task execution.

An MCP system implementation based on C++, including host, client, and server components, supporting interaction with LLM through the command line and calling various tool services.

The Chatvolt MCP Server is a TypeScript-based application designed to extend the capabilities of AI agents by providing a set of tools to enable them to interact with the Chatvolt platform. This project serves as a bridge between AI models and the Chatvolt API, supporting operations such as managing agents, querying data storage, and handling CRM scenarios, thereby automating complex workflows and providing a natural language interface for the Chatvolt platform.

The MCP Gateway is an advanced AI infrastructure middleware solution that acts as a proxy gateway for model context protocol (MCP) servers, providing unified interfaces, sensitive information filtering, and lifecycle management functions.

A browser automation service based on the MCP protocol, supporting natural language control of browser operations

An MCP server that provides WHOIS query services

A Django application that implements a Firebase Model Context Protocol (MCP) server, enabling AI agents to interact with Firebase services through a standardized protocol and providing 14 tools such as authentication, database, and storage.

Alibaba Cloud Wuying AgentBay is a cloud infrastructure designed for AI Agents, providing one - click configuration tools and an execution environment, supporting rapid integration and server - based operation.

The Ultimate MCP Server is an AI agent operating system based on the Model Context Protocol (MCP), offering dozens of powerful tool capabilities, including cognitive enhancement, tool usage, and intelligent orchestration. The system exposes functions through standardized MCP tools, enabling advanced AI agents to access a rich tool ecosystem and specialized services while optimizing costs, performance, and quality.

adb - mcp is a proof - of - concept project aiming to provide an interface for LLMs through the MCP protocol to create an AI agent for controlling Adobe tools (such as Photoshop and Premiere). This project includes the MCP server, Node command proxy server, and Adobe application plugins, supporting natural language instruction operations on Adobe software and suitable for image and video editing automation.

ACI.dev is an open-source AI agent tool infrastructure that provides multi-tenant authentication, permission management, and dynamic discovery functions for over 600 pre-integrated tools. It supports calls through a unified MCP Server or a lightweight SDK, simplifying the development of production-level AI agents.

A WhatsApp MCP server based on TypeScript and the Baileys library that connects personal WhatsApp accounts to AI agents to enable functions such as message search and sending.

LLM Gateway is a server based on the MCP protocol that supports advanced AI agents (such as Claude 3.7) to intelligently delegate tasks to lower - cost LLM models (such as Gemini Flash), achieving cost optimization and performance balance.

This project demonstrates how to run n8n workflows in a local Docker environment, integrate an AI agent with external tools (such as web search) through the Model Context Protocol (MCP), and use npx to dynamically start the MCP service to achieve dynamic discovery and use of tools.

Azure MCP Hub is a platform that helps developers quickly build, run, or reuse Model Context Protocol (MCP) servers. It supports multiple programming languages and AI frameworks, enabling AI agents to call real APIs.

A universal file viewer MCP server that provides read access to any folder in the file system for MCP clients, facilitating AI agents to access multiple repositories or other files.

The Brex MCP Server is a bridge connecting AI agents with the Brex financial platform, providing functions for financial data interaction.

Email MCP is a simple Model Context Protocol server that adds email capabilities to AI agents, supports POP3 and SMTP protocols, and provides functions for sending, receiving, and managing emails.

automcp is a tool that can convert existing AI agent frameworks (such as CrewAI and LangGraph) into MCP protocol servers, enabling standardized interface access. It supports rapid deployment, multi - framework adaptation, and provides two transmission modes: SSE and STDIO.

Octagon MCP is a market data model context protocol server that integrates the Octagon market intelligence API, providing AI agent services for public market data, private market data, and deep research.

MCP - AWS is an AI - based application that manages AWS EC2 instances through OpenAI agents and the MCP server, supporting natural language commands to create and terminate instances.

A lightweight MCP server based on Python that interacts with local ComfyUI via WebSocket to enable programmatic image generation by AI agents.

GenPilot is a tool that simplifies the creation and management of single/multi - agent systems for generative AI. It supports the MCP protocol and provides terminal and web interfaces for rapid development and deployment.

An MCP server integrated with Apache Kafka, providing message publishing and consumption functions for LLM and agent applications

The MCP Agent Server is a hub platform that connects AI clients with intelligent agents, supporting the creation of multi - specialized agents, combined agent workflows, and the integration of various AI tools and services.

The first open-source MCP server that enables full-featured AI control of a remote macOS system without the need to install additional software, providing complete desktop operation capabilities.

The MCP Browser Proxy is a powerful integration of the Model Context Protocol, providing autonomous browser automation capabilities for Claude Desktop and supporting functions such as navigation, screenshot, DOM interaction, JavaScript execution, and API requests.

This project provides two implementations of the MCP server, connecting Claude Desktop with Azure search capabilities and supporting document and web content search through Azure AI agent service (recommended) or direct Azure AI Search integration.

This project is a simplified implementation based on the MemGPT research paper, built using Spring Boot and Spring AI, providing two integration methods: REST services and MCP servers, and including core agent functions and chatbot applications.