AI 机器学习 资源

Tested and Compatible with OpenAI ChatGPT, Azure OpenAI Service, Perplexity AI and Llama!

This README is an agentic workflow

DEEPPOWERS is a Fully Homomorphic Encryption (FHE) collaboration framework built for MCP (Model Context Protocol), aiming to provide end-to-end privacy protection and highly efficient computation for the upstream and downstream ecosystems of the MCP protocol. By deeply integrating the FHE framework with the MCP protocol, we are dedicated to creating a secure, efficient, and scalable computing framework for MCP. This ensures that data remains encrypted throughout transmission, storage, and computation, while also supporting complex computing logic, eliminating unnecessary data transmission and computation, and thereby rapidly improving MCP's operational efficiency.

DeepSeek V3 doubao-1.5 pro Grok 3 clouad 3.7

Model Context Protocol (MCP) is like a USB for AI tools - it provides a standardized way for AI agents to discover and use different capabilities. Think of it as plugging in new abilities for your AI agents! With our flexible dictionary-based implementation, agents can easily discover and use tools without needing to know their implementation details.

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.

MCP server for vibe-tools - extends AI editor's capabilities with custom tools

Cross-platform Macos | Windows | Linux | iOS | Android AI Chat Client

Self Hosted Site AI Search, LLMs.txt, MCP Server that crawls your content. 1-Click Deploy on Vercel.

TLDR: Use Claude to control or ask questions about your Altium project. This is a Model Context Protocol (MCP) server that provides an interface to interact with Altium Designer through Python. The server allows for querying and manipulation of PCB designs programmatically.

Spring Boot Spring AI Java (MCP) Server AI Spring AI MCP JSON MCP Server

A Model Context Protocol (MCP) server enables artificial intelligence assistants to directly query data results. Users can obtain data results from DataFocus using natural language.

Mcpixir is the open source way to connect any LLM to any MCP server and build custom agents that have tool access, without using closed source or application clients.

haiku.rag is an MCP tool with RAG (Retrieval-Augmented Generation) capabilities.

CONTROL YOUR X THROUGH LLM AGENTS.

O projeto MCP (Model Context Protocol) visando o aprendizado desta nova tecnologia utilizando bibliotecas atuais em python, ferramentas que usam servers de servios que so gerenciados por agentes-llm's. Atualmente irei integrar pelo menos 2 serves (a proposta escalar)

This folder contains a general-purpose base implementation of the Model Context Protocol (MCP) for building AI-powered applications. It provides a standardized way to create MCP servers and clients that can be used to integrate LLMs into your applications.

A Rust implementation of the Model Context Protocol (MCP), providing a standardized way for AI models to access external context and resources.

A Model Context Protocol (MCP) server that allows LLMs to interact with Subgraphs available on The Graph Network.

A Model Context Protocol (MCP) server that facilitates structured, progressive thinking through defined stages. This tool helps break down complex problems into sequential thoughts, track the progression of your thinking process, and generate summaries.

This MCP (Model Context Protocol) server provides AI assistants with the ability to search the web, get news, and perform research using the You.com API. Feedback welcomed.

MCP_Voice_Transfer .

Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. It provides a standardized method for connecting LLMs with necessary context in AI-based IDEs, chat interfaces, custom AI workflows, and more.

Demo: Watch Here

The goal is to build a codeforces's mcp server for users to get codeforces info by LLM.

This document provides an overview of a modular architecture designed to handle user queries through a large language model (LLM). The system consists of four main components working together to manage client communication, session context, and LLM interaction.

MLX90640 is a thermal camera (32x24 pixels) using Far InfraRed radiation from objects to measure the object temperature. https://www.melexis.com/mlx90640 The python package "mlx90640-driver" driver interfaces the MLX90640 and aims to facilitate rapid prototyping.

Welcome to the Winx Code Agent repository! This project offers a high-performance code agent written in Rust. It combines the best features of WCGW and Serena to deliver maximum efficiency and semantic capabilities.

MCPSO, multi-swarm cooperative particle swarm optimizer, inspired by the phenomenon of symbiosis in natural ecosystems. MCPSO is based on a masterslave model, in which a population consists of one master swarm and several slave swarms. The slave swarms execute a single PSO or its variants independently to maintain the diversity of particles, while the master swarm evolves based on its own knowledge and also the knowledge of the slave swarms. According to the co-evolutionary relationship between master swarm and slave swarms, two versions of MCPSO are proposed, namely the competitive version of MCPSO (COM-MCPSO) and the collaborative version of MCPSO (COL-MCPSO), where the master swarm enhances its particles based on an antagonistic scenario or a synergistic scenario, respectively. In the simulation studies, several benchmark functions are performed, and the performances of the proposed algorithms are compared with the standard PSO (SPSO) and its variants to demonstrate the superiority of MCPSO.

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits Brandon Radosevich*, John Halloran* Paper: https://www.arxiv.org/abs/2504.03767

A portable, Dockerized Python tool that implements a Model Context Protocol (MCP) for audio transcription using OpenAI's Whisper modelsand even ships with a Streamlit-powered web UI so you can upload an audio file and download the transcription as JSON.

This is a Model Context Protocol (MCP) tool that allows Claude to interact with the ChatGPT desktop app on macOS.

A Ruby on Rails engine for the Model Context Protocol (MCP) - connect your Rails apps to AI tools with minimal effort.

A streamlined server deployment solution for Model Context Protocol (MCP) using FastMCP. This project simplifies the process of running and managing multiple MCP servers with different transport methods.

A Python-based MCP (Model Context Protocol) server that enables AI assistants to interact with an Unraid server through the official Unraid GraphQL API.

Pytorch Implementation of the paper: "MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One Day"

A collection of Model Context Protocol (MCP) servers for biomedical research, providing AI assistants with access to various biomedical databases and resources.

A sophisticated chat application that provides an enhanced interactive AI experience through a multi-agent architecture and support for multiple LLM providers. It features specialized agents, intelligent transfers, file integration, web capabilities, and a modular extension system.

A Go implementation of the Model Context Protocol (MCP), a standardized protocol for communication between LLM clients and context providers.

Model Context Protocol (MCP) library that provides resources and tools for AI agents (Chatbots, Coding agents, etc.) to understand and interact with domains specific tools and knowledge.

CyberMCP is a Model Context Protocol (MCP) server designed for testing backend APIs for security vulnerabilities. It provides a set of specialized tools and resources that can be used by LLMs to identify common security issues in APIs.

These two examples demonstrates how to create a multi-client application using the Model Control Protocol (MCP).

A Model Context Protocol (MCP) server that enables LLMs to interact directly the documents that they have on-disk through agentic RAG and hybrid search in LanceDB. Ask LLMs questions about the dataset as a whole or about specific documents.

NEWS: Version 1.0.0 is now published to npm! You can run Excalidraw MCP directly using npx excalidraw-mcp without installation. No setup required - just run and enjoy!

Get personalised workout recommendations directly in your inbox

A robust, free, ready-to-use Rails boilerplate for building AI-powered applications that integrate seamlessly with Claude AI using the Model Context Protocol (MCP). This boilerplate includes user authentication and OAuth2 provider capabilities out of the box.

"Unleash the Power of AI in Your WordPress Realm - Setting the Standard for MCP Excellence!"

A Model Context Protocol (MCP) server that provides text-to-speech capabilities using the Kokoro TTS engine. This server exposes TTS functionality through MCP tools, making it easy to integrate speech synthesis into your applications.

Check out my chatbot code using MCP :D

Projeto completo para uma aplicao conversacional com:

Cursor Claude Google Gemini API . , , Gemini .

Your users are increasingly getting accustomed to using natural language to communicate with AI apps like ChatGPT, Claude Desktop, and Cursor. With MCP, you can build AI-powered apps that integrate with these apps, allowing you to meet users where they are.