# AI agent

The Agentic MCP Client is an independent AI agent runner that interacts with models such as Claude, BedRock, and OpenAI through MCP protocol tools, supporting autonomous cloud operation and secure system interaction.

AI agent robot project based on multi-MCP servers

The Ultimate MCP Server is an AI agent operating system based on the Model Context Protocol (MCP), providing a rich toolset and intelligent task delegation function, supporting multi-LLM provider integration, optimizing cost and performance, and automating complex workflows.

This project demonstrates how to integrate OpenAI, Azure OpenAI, and GitHub models through the MCP protocol to build a terminal application for a TODO list agent. The project includes three major components: MCP host, client, and server, supports HTTP and SSE protocols, and provides tool invocation and database storage functions.

Demonstrate connecting the Keboola Registry API to the MCP server through the CrewAI wrapper, enabling AI agents to call registered skills.

The MCP Dust Server is a server-side implementation of the Model Context Protocol (MCP) for interacting with Dust AI agents. The project consists of an MCP server and a test client, supporting real-time streaming responses, the complete JSON-RPC 2.0 protocol, session management, and other functions. It can be integrated into development environments such as Windsurf IDE and Claude Desktop.

An MCP server implementation for AdGuard Home, supporting querying and managing DNS records, filtering rules, etc. through an AI agent.

An MCP server that supports Claude for API testing, providing general API testing and OpenAI - specific tools

A Gmail email management server based on the Model Context Protocol (MCP), supporting searching, reading, deleting, and sending emails through an AI agent. It needs to be used with a voice interaction client.

MCPML is a Python framework for building servers compliant with the Model Context Protocol (MCP), supporting CLI tools and OpenAI agent functions, and providing features such as dynamic loading and structured output.

The Firebolt MCP Server is a service that implements the model context protocol, which can connect LLMs (large language models) with the Firebolt data warehouse, enabling AI assistants to directly query data, generate insights, and access documentation resources.

MCP speech synthesis server based on Edge-TTS

This is a full-stack application based on Cloudflare Workers that combines a React front-end, REST API, and MCP server functionality, using Stytch for user authentication. The project demonstrates how to extend a traditional application into a solution that supports AI agents.

automcp is a tool that can easily convert existing AI agent frameworks (such as CrewAI, LangGraph, etc.) into MCP servers to achieve standardized interface access. It supports the adaptation and deployment of multiple frameworks and provides functions for quick startup and configuration.

Intelligent product search system based on MCP service and OpenAI Agent SDK

This is an MCP server implementation project based on SearXNG, providing privacy - protected search capabilities for AI agents. The project is deployed through Docker containerization, supports two transport protocols, SSE and Stdio, and can be easily integrated into MCP - compatible clients.

The Azure MCP Server is a server that implements the MCP protocol, providing seamless connection between AI agents and Azure services (such as Storage and Cosmos DB), and supporting the conversion of natural language commands into Azure operations.

TEN Agent is a multi-functional AI agent framework that integrates real-time vision, voice recognition, and screen sharing detection capabilities, and supports rapid expansion and development.

MCPlite is a Python MCP service framework similar to FastAPI, which allows developers to easily define and expose server-side capabilities (such as tools, functions, or resource access) for programmatic calls by AI agents in host applications.

Solana MCP is a protocol server designed for AI agents, providing a standard interface for interacting with the Solana blockchain and DeFi protocols, supporting operations such as balance query, fund transfer, and trading.

Grasp is an open-source and self-hostable humanized browser automation tool that supports the MCP and A2A protocols and can seamlessly integrate with various AI applications. Through Docker containerization deployment, it provides a browser operation experience controlled by natural language.

Filesystem MCP is a Node.js-based Model Context Protocol server that provides secure, relative-path file system access services for AI agents (such as Cline and Claude).

The LINE Bot MCP Server is a server that implements the Model Context Protocol (MCP), used to connect an AI agent to a LINE official account and supports sending text and flexibly laid-out messages.

The Azure AI Agent Service MCP Server integrates the functions of Azure AI Foundry, supports connecting to existing Azure AI agents, and provides capabilities such as security authentication, session memory, and multi-tool invocation.

This project implements an adapter between Langchain and the Box MCP server, integrating AI capabilities through tools and agents, supporting dynamic tool loading, creating React-style agents, and providing a friendly console interaction interface.

An AI-driven browser automation server based on the MCP protocol, supporting natural language control of web page operations and in-depth web research.

MCP Kanban is a task management toolset designed for AI agents. It manages multi-session workflows through a kanban system, supports column capacity limits, an embedded database, and Web UI monitoring. It provides API interfaces for creating, moving, and deleting tasks, as well as preset prompt words to assist in project initiation and advancement.

mcp - searxng is an MCP server example designed for AI agents, which implements the external information search function through the open - source meta - search engine SearXNG. The project demonstrates how to integrate SearXNG and Microsoft's markdownify tool to convert web page content into Markdown - formatted text and communicate with MCP clients via the SSE protocol.

Project exploring MCP servers and AI agents

This project is an interaction server for the Open eClass platform based on the MCP protocol, supporting the SSO authentication system of the University of Athens. It provides functions such as course management and session maintenance, enabling AI agents to securely interact with the eClass platform.