AI 机器学习 资源

A modern template for agentic orchestration built for rapid iteration and scalable deployment using highly customizable, community-supported tools like MCP, LangGraph, and more.

MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

MyMCP is a Python application that enables parallel execution of multiple AI coding tasks using the Aider tool. It provides a framework for running multiple coding prompts simultaneously, improving efficiency and reducing execution time.

Welcome! This guide will help you use the Multi-cover persistence (MCP) machine learning approach for predicting polymer properties. We'll walk you through obtaining the data, setting up your environment, and executing the code to generate MCP features from your dataset.

An OpenStreetMap MCP server implementation that enhances LLM capabilities with location-based services and geospatial data.

A Model Context Protocol (MCP) server for YouTube video analysis, providing tools to get transcripts, summarize content, and query videos using Gemini AI.

Ontology MCP GraphDB SPARQL Ollama Claude Model Context Protocol (MCP) . Claude , AI .

LangChain-MCP-Adapters is a toolkit provided by LangChain AI that enables AI agents to interact with external tools and data sources through the Model Context Protocol (MCP). This project provides a user-friendly interface for deploying ReAct agents that can access various data sources and APIs through MCP tools.

This repo demonstrates both how to create an MCP server using LlamaCloud and how to use LlamaIndex as an MCP client.

Powerful Local AI Chat Application - Secure, Efficient, Personalized

This project demonstrates how to create an autonomous AI agent using LangChain, MCP (Multi-Component Protocol), and large language models like OpenAI's gpt-4o-mini. The agent is capable of interacting with tools such as Playwright via MCP to execute complex tasks programmatically.

Welcome to the Agents repository! This project empowers developers to build and deploy AI agents seamlessly on Cloudflare. Whether you're looking to create intelligent workflows or utilize durable objects, this repository provides the tools you need to get started.

DART API MCP(Model-assisted Capability Package). Claude .

A deep-dive guide into architecture patterns for building responsive, reliable AI coding agents.

Personal MCP Servers and Clients for LLM

The open-source ecosystem for building, discovering, and deploying Model Context Protocol servers and clients for enterprise environments.

A collection of MCP servers for enabling more present AI agents.

A terminal AI chat interface for any LLM model, with file context, MCP and deployment support.

Dive MCP Host is a language model host service based on the Model Context Protocol (MCP), providing a unified interface to manage and interact with various language models.

A Model Context Protocol (MCP) server that provides AI-powered visual analysis capabilities for UI/UX assessment. Compatible with Claude and other MCP-enabled AI assistants.

Magic aims to help enterprises of all sizes quickly build and deploy AI applications to achieve a 100x increase in productivity.

A Python-based MCP (Model Context Protocol) server for Xano that allows AI assistants like Claude to interact directly with your Xano instance. This is a standalone version optimized for local use with Claude Desktop and other MCP-compatible LLMs.

A Python package for interacting with LLMs via the MCP protocol.

A Model Context Protocol (MCP) server for interacting with AI agents through the Agent API by Coder.

This repository contains a collection of tools and protocols for interacting with Atlan services for AI agents. Each component is designed to provide specific functionality and can be used independently or together.

In today's rapidly evolving AI landscape, developers need flexible ways to interact with large language models (LLMs) while maintaining control over their applications. The Model Context Protocol (MCP) provides a standardized way for applications to communicate with AI models, and when combined with Amazon Bedrock's powerful foundation models, it creates a robust platform for building intelligent applications. In this post, we'll explore how to build custom client applications using the MCP client SDK and Amazon Bedrock Tool use.

El Model Context Protocol (MCP) es el componente central de nuestra herramienta para actualizar clsteres Amazon EKS. Define cmo se recopila, estructura y gestiona la informacin relevante ("Contexto") que se entrega a un modelo de Inteligencia Artificial, permitiendo automatizar la verificacin previa y la generacin de recomendaciones para el proceso de actualizacin.

A TypeScript implementation of a Model Context Protocol (MCP) server that integrates with Google's Gemini model using direct API calls.

The commercetools Agent Toolkit enables popular agent frameworks including LangChain, CrewAI, Vercel's AI SDK, and Model Context Protocol (MCP) to integrate with APIs through function calling. The library is not exhaustive of the entire commercetools API. It includes support for TypeScript and is built directly on top of the [Node][node-sdk] SDK.

A Model Context Protocol (MCP) server implementation that exposes Pearl's AI and Expert services through a standardized interface. This server allows MCP clients like Claude Desktop, Cursor, and other MCP-compatible applications to interact with Pearl's advanced AI assistants and human experts.

A MCP server that provides text-to-image generation capabilities using Stable Diffusion WebUI API (ForgeUI/AUTOMATIC-1111). It also supports optional image uploading to a Cloudflare ImgBed instance.

An open digital commons where autonomous AI agents meet, converse, and co-create

This is a lightweight AI-powered agent built using Model Context Protocol (MCP) and Claude Desktop. The agent exposes local file-handling tools (like listing files, reading files, and checking file sizes) which Claude can interact with using natural language.

Questo progetto implementa un sistema multi-agente per la scrittura di libri, utilizzando Python e il framework smolagents.

Unlock your Geekbot data within your LLM applications

This repository provides a set of utilities to build an MCP server (Model Context Protocol) that you can integrate with your conversational AI client.

A knowledge-graph-based memory system for AI agents that enables persistent information storage between conversations.

An MCP server designed to manage Data Products - enabling AI-assists to discover discover and query data products in a governed way.

An MCP (Model Context Protocol) service that allows Claude to generate images using OpenAI's DALL-E models.

A Model Context Protocol (MCP) server that creates and maintains a semantic knowledge graph of code generated by Claude. Powered by LlamaIndex, this allows maintaining context across sessions with advanced semantic search capabilities without requiring the entire codebase to be present in the context window.

A simple Model Context Protocol (MCP) application that provides filesystem operations using Ollama local LLM. This project demonstrates the integration of local AI models with filesystem operations through a client-server architecture.

Agent-ready SEO content generation tool with MCP and Tool profile support for modern LLM ecosystems.

Shadcn-vue MCP Server is a powerful AI-driven tool that helps developers instantly create beautiful, modern UI components through natural language descriptions. It integrates the shadcn-vue component library and tailwindcss, seamlessly connects with mainstream IDEs, and provides a streamlined UI development workflow.

A Model Context Protocol (MCP) server that provides AI assistants access to AWS CloudWatch Logs for analysis, searching, and correlation.

A Cloudflare Worker-based MCP (Model Context Protocol) Server with streamable HTTP transport support. This server provides various tools and integrations for AI assistants to interact with external services and APIs.

eeg-mcp-project/ backend/ brainflow_server.py # MCP APIs (read, visualize, filter, features) rag_server.py # RAG API server using Ollama LLM + Vector DB vectorstore.py # Vector DB Population script .env # API keys & env variables (ignored in git) uploads/ # Temp uploads folder data/ # EDF EEG data files vectorstore/ # Persisted Chroma Vector DB files requirements.txt # Python dependencies list .gitignore # Ignore node_modules, .env, cache files README.md # This file

This server is a middleware that enables large language models (like Claude and VS Code) to interact directly with PlayFab services. Acting as a secure and efficient translator, it connects your AI assistant with various PlayFab functionalities, such as item search, segment inquiries, player profile lookups, inventory management, and PlayFab ID conversion.

This is a single-page spec for solving the context problem for large language models.

This repo introduce a Multi-Agents system in the field of consultant for sales product, with MCP SSE server include functions for create orders if users want to buy a products and retrieve products from MongoDB, powered by CrewAI.

Natural language interface for scRNA-Seq analysis with Liana through MCP.

Model Context Protocol (MCP) AI MCP LLM

A modular AI-powered framework for ingesting multimodal data (images, PDFs, text), processing them via agents and pipelines, and storing structured insights into MongoDB.

Airtap is a powerful Model Context Protocol (MCP) server that provides seamless integration with Android devices in a sandbox environment. It enables AI agents, LLMs, and applications to interact with Android OS programmatically through a standardized API.

A Model Context Protocol (MCP) server for generating and editing images using OpenAI's GPT-Image-1 API. This project provides an API interface to generate or edit images based on text prompts and input images, with results stored and served via an S3-compatible object storage server.