AI 机器学习 资源

RagLit is a Model Context Protocol (MCP) server designed to facilitate document processing and retrieval for Retrieval Augmented Generation (RAG) pipelines. It acts as an interface to a PostgREST-compatible backend API (such as one provided by Supabase or a self-hosted PostgREST instance) that handles the persistent storage of document chunks, vector search, and metadata filtering using PostgreSQL and the pgvector extension.

"Combine A2A and MCP to create advanced, distributed agentic systems!"

A comprehensive collection of practical examples, tutorials, and recipes showcasing how to build powerful LLM-powered applications using various frameworks and tools.

This project is a hands-on exploration of the Model Context Protocol (MCP), an open standard developed by Anthropic to simplify the integration of AI applications with external tools and data sources. By following this guide, you'll understand how to build and deploy MCP servers and clients, enhancing AI applications with rich contextual information.

AI-Powered Fact-Checking Prototype with MCP Integration

A Model Context Protocol (MCP) server for CMF Server. This server exposes CMF Server functionality as tools that can be used by AI assistants.

MCP Web UI is a web-based user interface that serves as a Host within the Model Context Protocol (MCP) architecture. It provides a powerful and user-friendly interface for interacting with Large Language Models (LLMs) while managing context aggregation and coordination between clients and servers.

A framework for creating chatbots and AI agent workflows. It enables seamless integration with multiple AI models, including OpenAI, LLaMA, deepseek, Stable Diffusion, and Mistral, through a unified access layer. Intelli also supports Model Context Protocol (MCP) for standardized interaction with AI models.

http://k8gege.org/Ladon/ChatGPT.html

Natural language interface for Copy Number Variation (CNV) inference from scRNA-Seq data with infercnvpy through MCP.

Model Context Protocol What is Model Context Protocol?

javaAILangchain4jSpringAIRAGMCPFunction Calling

or

An MCP server for Avunite AI (and others) to interface with Barkle. USING BARKLE FOR AI TRAINING IS STRICTLY FORBIDDEN FOR ALL INCLUDING AVUNITE

mcp chatbot with datasources as sql database, mongodb database, arxiv, google drive, news api, google custom apis and wikipedia.

This application provides a chat interface for interacting with multiple Large Language Models (LLMs). It supports models from OpenAI, Anthropic, Google (Gemini), xAI (Grok), and custom models via OpenRouter. Key features include text and image input processing, file text extraction, and integration with MCP servers for tool usage.

A Model Context Protocol (MCP) implementation for Key Opinion Leader sentiment analysis using the Masa AI API.

A demonstration of using LangGraph with Model Context Protocol (MCP) for filesystem operations.

Doris MCP (Model Control Panel) Server Python FastAPI MCP (Model Control Panel) "(Tools)" Apache Doris (LLM) SQL (NL2SQL)

mcpsandbox is a MCP Client, works on VPS, sandbox MCP environment for all AI developers!

pentestMCP provides a powerful bridge between Large Language Models (LLMs) and practical penetration testing tools through the Model Context Protocol (MCP). This project functions as an MCP Server, exposing a curated suite of over 20 standard security assessment utilities (Nmap, Nuclei, ZAP, SQLMap, etc.) as callable 'tools'. This allows AI agents within MCP-compatible clients (like Claude Desktop or specific VS Code setups) to leverage these utilities for automated and interactive security analysis tasks.

Allows a LLM to explore a codebase and answer questions about it. It can explore the folder structure while taking into account .agentignore files. It can also read from files, however, it cannot modify the codebase. This server provides a read-only interface to the codebase.

This project implements a RooCode-inspired workflow system for Cursor, enabling collaborative AI development with specialized roles.

This repository implements a powerful Multi-Agent Control Protocol (MCP) system for distributed AI coordination, intelligent dialogue, and agentic planning. The system orchestrates multiple agents, tools, and strategies to solve complex user queries through dynamic, extensible, and introspective agentic flows.

HuggingFace Model Context Protocol (MCP) Course

A minimal FastMCP 2.x server in TypeScript that exposes one RPCretrieveDocs(question)which returns raw ranked chunks from OpenAI File Search.

TinyAgents: LLM + MCP Tools

A local memory system to enhance AI interactions in Cursor

llmbasedos is a minimal Arch Linux based distribution designed to expose local capabilities (files, mail, sync, agents) to various "host" applications (LLM frontends like Claude Desktop, VS Code plugins, ChatGPT, etc.) via the Model Context Protocol (MCP).

An intelligent Stock Recommender system powered by LangChain, A2A and MCP

Windows MCP is a lightweight, open-source project that enables seamless integration between AI agents and the Windows operating system. Acting as an MCP server bridges the gap between LLMs and the Windows operating system, allowing agents to perform tasks such as file navigation, application control, UI interaction, QA testing, and more.

A Node.js server implementing the Model Context Protocol (MCP) for Claude AI models, allowing you to define and use custom prompt templates with a modular, category-based organization system.

This example shows an Orchestrator workflow which dynamically plans across a number of agents to accomplish a multi-step task.

WIP!! Please send PRs.

A Spring Boot application that implements the Model Context Protocol (MCP) server, providing AI-powered tools for different platforms. This server can be integrated with Claude Desktop and other MCP-compatible clients.

pure python gui application with streamlit ollama and fastmcp

An MCP (Model Context Protocol) server that provides access to the Xyte Organization API, enabling AI assistants to interact with Xyte devices, commands, tickets, and more.

Part of the VibeSafe OSS Stack, this MCP (Model Context Protocol) server allows AI agents and LLM-powered IDEs like Cursor to run real-time security scans on your codebase.

GDB MCP (Model Context Protocol) AI MCP GDB

Welcome to the OSMMCP repository! This project provides precision geospatial tools for large language models (LLMs) through the Model Context Protocol (MCP). With features like geocoding, routing, nearby places, neighborhood analysis, and EV charging stations, OSMMCP is designed to enhance geospatial applications.

MCP (Model Context Protocol) server that utilizes the Google Gemini Vision API to interact with YouTube videos. It allows users to get descriptions, summaries, answers to questions, and extract key moments from YouTube videos.

The Deep Research Privacy App is a privacy-focused research tool that automates exploring topics in depth. It uses the Brave Search API along with optional token classification from the Venice LLM API. The app supports both CLI and browser-based terminal interfaces, letting you securely perform research, manage accounts, and enhance queries with metadata from external APIs.

MCP server to let LLM take full control on your device by providing screen automation toolkit for controlling and interacting with graphical user interfaces. Good for automation, education and having fun.

A modern, lightweight arXiv paper browser built with React + Vite. Features a custom-built arXiv API integration for reliable paper fetching and time-based filtering.

This is a project template for Agentic Coding with Pocket Flow, a 100-line LLM framework, and your editor of choice.

This project is an MCP (Multi-Agent Conversation Protocol) Server for the given OpenAPI URL - https://api.apis.guru/v2/specs/amazonaws.com/machinelearning/2014-12-12/openapi.json, auto-generated using AG2's MCP builder.

This is an MCP server that generates text using both OpenAI's GPT-3.5 and Google's Gemini Pro models in parallel.

The Model Context Protocol (MCP) is a standard for helping AI tools and LLMs talk to applications and services like Directus.

This repository contains the Context3D MCP Server, a specialized component that integrates the advanced Context3D AI-powered 3D asset generation capabilities with the Model Context Protocol (MCP). While the core Context3D services handle the complex process of generating production-ready 3D models from text prompts or reference images using proprietary diffusion models and extensive datasets, this MCP server provides a standardized interface to access these capabilities via MCP.

A lightweight, command-line interface (CLI) client for interacting with Language Model (LLM) providers (Anthropic, OpenAI, Google Gemini, DeepSeek) and Model Context Protocol (MCP) servers. This client utilizes the official @modelcontextprotocol/sdk for robust communication with MCP-compliant tool servers.

A Model Context Protocol (MCP) server for using HuggingFace computer vision models as tools for LLM use.

The Alation AI Agent SDK enables AI agents to access and leverage metadata from the Alation Data Catalog.