AI 机器学习 资源

Unleash the power of AI to streamline HR leave management. This repository provides the blueprint for your very own "Model Context Protocol" (MCP) server, designed to intelligently handle leave-related queries. Think of it as giving your HR team a smart assistant that speaks the language of leave policies!

Collection of model-centric MCP servers

AI-Agent is a modern AI assistant that automates tasks like sending emails and creating Google Calendar events using natural language prompts. Its built with React, uses Google OAuth for secure authentication, and is powered by the Model Context Protocol (MCP) for smooth communication between the client and server.

An AI agent using Pydantic AI, integrated with the Context7 MCP server and OpenAI models. Includes a CLI for interactive chat and persistent conversation history.

A lightweight server that exports CAMEL framework toolkits as MCP-compatible tools.

This project is an MCP (Multi-Agent Conversation Protocol) Server for the given OpenAPI URL - https://api.apis.guru/v2/specs/amazonaws.com/sagemaker/2017-07-24/openapi.json, auto-generated using AG2's MCP builder.

Fastapi-MCPServe es un microservicio basado en FastAPI que implementa el protocolo MCP (Model Context Protocol). Su objetivo es brindar herramientas y capacidades extendidas a modelos de inteligencia artificial, actuando como una capa de servicios para tareas complejas.

A local Model Context Protocol server that stores project context (bookmarks, files, notes) and exposes a REST + WebSocket API so multiple AI models (OpenAI GPT-4o, Anthropic Claude 3, local LM Studio) can share the same information.

An MCP server that generates contextual prompts from codebases, making it easier for AI assistants to understand and work with your code repositories.

An server that enables AI assistants to interact with Flutterwave, providing tools for confirming transactions, send failed hooks, and more.

Winodws\Linux\MacOS

The Model Context Protocol (MCP) is an open-source standard introduced by Anthropic in November 2024 to streamline how artificial intelligence models, especially large language models (LLMs), integrate with external data sources and tools. It serves as a universal interface, simplifying the process of connecting AI systems to diverse resources like databases, APIs, cloud services, or local applications.

A Rust implementation of an SSH client server with Model Context Protocol (MCP) integration, allowing Large Language Models (LLMs) to connect to a SSH server and utilize SSH features.

This is a Server-Sent Events (SSE) API that fetches and streams the latest headlines from top AI and app development RSS feeds.

AgenticMCP (Agentic Model Communication Protocol) is an open source TypeScript-based command-line interface (CLI) tool that enables users to leverage various Large Language Models (LLMs) as predefined agents with specific roles and contexts. It provides a unified, extensible, and secure interface for interacting with LLM providers such as OpenAI, Anthropic, Google, and more.

A tool for detecting fake news using MCP.

AiCore is a comprehensive framework for integrating various language models and embedding providers with a unified interface. It supports both synchronous and asynchronous operations for generating text completions and embeddings, featuring:

The MCP Chain of Draft (CoD) Prompt Tool is a powerful Model Context Protocol tool that enhances LLM reasoning by transforming standard prompts into either Chain of Draft (CoD) or Chain of Thought (CoT) format. Here's how it works:

A server that exposes FFmpeg functionality through the Model Context Protocol (MCP). This enables AI Large Language Models (LLMs) such as Claude to interact with FFmpeg to process video and audio files.

AutoInvestAIMCP (Multi-Component Processing)

Documentation context provider for LLMs via MCP. This server enables AI models to seamlessly access and query your local markdown technical documentation.

A desktop application for interacting with AI models via the Model Context Protocol (MCP), providing a powerful interface for chat conversations with tool execution capabilities.

A Go implementation of a Perplexity Search MCP server that allows large language models (LLMs) to access the Perplexity search API through the Model Context Protocol (MCP).

The GemCP app is a cross-platform desktop application that creates a seamless chat interface for Google's Gemini AI models with extensible capabilities through a Model Context Protocol (MCP) framework.

Demo project for Model Context Protocol

A integrao entre o Model Context Protocol (MCP) e a computao quntica representa uma fronteira inovadora na interseo entre inteligncia artificial e processamento quntico. Este documento explora como podemos utilizar o MCP para criar interfaces entre modelos de IA e computadores qunticos atravs do Amazon Braket, permitindo que assistentes de IA possam acessar, controlar e interpretar resultados de computao quntica de forma padronizada e eficiente.

Connect, setup, secure and seamlessly manage LLM models using an Universal/OpenAI compatible API

A lightweight self-hosted platform for hosting and configuring MCP-enabled chat widgets remotely. Deploy, create and manage AI chat widgets to embed on your website. Add an MCP client toyour websites, dashboards, and applications with access to advanced AI models and external tools.

A secure Python code execution server that enables LLMs to run Python code safely in isolated Docker containers. The server supports:

Molecule-MCP: A model-context-protocol server for molecules. Molecule-MCP connects molecule science releated tools to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control these tools and act as a co-scientist. This integration enables prompt assisted molecule modeling.

Welcome to PDFMathTranslate! This repository focuses on translating scientific papers in PDF format while preserving their original layout. With the help of advanced AI technologies, our tool supports multiple languages, including English, Chinese, Japanese, Korean, and Russian. It integrates with various translation services like Google, DeepL, Ollama, and OpenAI. You can access the latest releases here.

RhinoMCP connects Rhino to AI agents through the Model Context Protocol (MCP), allowing AI agents to directly interact with and control Rhino. This integration enables prompt assisted 3D modeling in Rhino 3D.

A Model Context Protocol (MCP) server for integrating AI assistants with Anki, the popular spaced repetition flashcard software.

HYDRA-AI is a modern AI chat application built with React, TypeScript, and Tailwind CSS. The project utilizes the latest web technology stack to provide a smooth, responsive user experience for blockchain project analysis and AI assistant interactions.

LLM-agnostic MCP Server- node

Notion-MCP-Agent is a personal project that turns your Notion workspace into a live, AI-driven knowledge hub. It pairs a FastMCP server that exposes tools for connected Notion pages with a Tkinter-based GUI built on LangChain and GPT-4o (or any compatible LLM). Together, they enable real-time page reading, writing, summarisation, and structured-note generation through a chat-style interface.

NewsBot-MCP is a Kotlin-based conversational chatbot that delivers real-time news content using the Model Context Protocol (MCP).

Your AI-assisted mentor for Blender.

The Model Context Protocol (MCP) is a standardized framework for managing and optimizing context handling in large language models (LLMs). This protocol aims to improve the efficiency, relevance, and coherence of model outputs by providing structured methods for context management.

friendsofhyperf/mcp Hyperf Model Context Protocol MCP AI

MCP(Model Context Protocol) server for Youtube search, transcript etc built using Java MCP SDK and Spring AI. For transcript extraction alone Javascript is used.

English |

UnityMCP is a powerful Unity Editor plugin that implements the Model Context Protocol (MCP), enabling seamless integration between Unity and AI assistants. It provides real-time editor state monitoring, remote command execution, and comprehensive logging capabilities.

LLVM pass that inserts references to string constants at random locations in the program.

An AI-powered travel assistant connected to Claude via MCP, designed to help users explore the Amazon Rainforest from planning routes to discovering nearby hotels and adventure spots.

This repository contains a basic example of how to build an AI agent using the Model Context Protocol (MCP) with an open LLM (Meta Llama 3), OpenAI or Google Gemini, and a SQLite database. It's designed to be a simple, educational demonstration, not a production-ready framework.

This project uses AI to generate complete, functional applications based on user descriptions. It leverages the OpenRouter API to design, generate, and validate application code. The Flask interface provides an intuitive and modern way to create applications without writing code.

Welcome to the AI Engineering Hub!

A little experiment with Amazon Q, Model Context Protocol (MCP), and tmux to create a news aggregation system that runs entirely in your terminal. It fetches and summarizes articles from various news sources using multiple agents working in parallel.

A chatbot implementation that combines Ollama with MCP (Machine Control Protocol) tools support. This allows the chatbot to use tools to perform tasks like calculations while maintaining conversation memory.

KelvinQiu802/llm-mcp-rag Python LLMMCP RAG

Supercharge your AI Agent's capabilities! PyMCPAutoGUI provides a bridge between your AI agents (like those in Cursor or other MCP-compatible environments) and your computer's graphical user interface (GUI). It allows your agent to see the screen , control the mouse and keyboard , and interact with windows , just like a human user!

This sample project demonstrates how to build a Model Context Protocol (MCP) server for managing a to-do list. By leveraging the MCP standard, this server enables AI agents and other compatible applications to interact with and control to-do list functionalities through a structured and discoverable interface.

This project is a lightweight, AI-native MCP (Model Context Protocol) server that integrates with Zendesk's REST APIs. It allows GPT-based AI agents (e.g. OpenAI, LangChain) to fetch real-time customer and organization context dynamically.