AI 機器學習 資源

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

...

A smart context management system for coding projects that uses knowledge graphs and vector databases for intelligent storage and retrieval.

A Model Context Protocol (MCP) server for fal.ai that enables natural language image generation and processing through Claude, Cursor, and other MCP-compatible clients.

Unity Code MCP is a coding focused Model Context Protocol (MCP) server that enables AI agents to write Unity code autonomously.

An OpenAI-powered MCP server for natural language querying of historical weather data from MongoDB Atlas. Supports temperature, wind, pressure, visibility, and station metadata retrieval using conversational queries.

Talk to your database using WAII and MCP through Claude Desktop

A demo of the ModelContextProtocol (MCP) using the Anthropic AI SDK.

FastMCP LangGraph ReAct Agent

MCP server that allows agentic interaction with the Lean theorem prover via the Language Server Protocol using leanclient. This server provides a range of tools for LLM agents to understand, analyze and interact with Lean projects.

A powerful, modular Model Context Protocol (MCP) server for WordPress and Elementor. This server provides AI assistants with scalable capabilitiesfrom basic content management to advanced page buildingthrough an intelligent configuration system.

Gergy AI is an intelligent assistant powered by Model Context Protocol (MCP) architecture, designed to provide cross-domain intelligence across five key life areas: Financial, Family, Lifestyle, Professional, and Home management.

Complete knowledge management for AI assistants MCP server with Elasticsearch search and document management.

The goal of this workshop for you to familiarize yourself with how LLMs can be augmented using tools and MCP.

This is an intelligent Airbnb Search Assistant built using Agno, MCP, Google Gemini, and Streamlit. The application provides users with a smart chatbot interface that retrieves Airbnb listings based on user preferences such as location and budget through natural conversation.

MCPToolBench++ is a large-scale, multi-domain AI Agent Tool Use Benchmark. As of June 2025, this benchmark includes over 4k+ MCP Servers from more than 45 categories collected from the MCP and GitHub communities. The dataset comprises both single-step and multi-step tool calls across different categories. And we evaluated some SOTA Agent LLMs and RAG-Based Systems.

(MCP)AI

MCPModel Context ProtocolAIAI

Token-Compressed Engineering Rule Framework with Fractal MCP Architecture

A powerful multi-agent AI system built using LangChain, MCP (Model Control Protocol), and Streamlit. This app connects multiple external tools (Math, Weather, and Web Search) to a single AI agent for real-time interaction and factual reasoning.

Unlocking next-generation knowledge discovery through state-managed, adversarial LLM agents.

Open source MCP client for PUO Memo - the universal memory system for AI assistants.

The mcp-server is an AI-integrated service catalog plugin that exposes deep structural insights into our large codebase. It allows AI agents like Claude Desktop, Gemini CLI, or other LLM-powered tools to explore the system architecture in a programmatic, structured way.

An intelligent file management system that combines AI-powered automation with human oversight for safe file operations. The system uses OpenAI to understand natural language requests and executes file operations while requiring human approval for high-risk actions via Slack.

An MCP (Model Context Protocol) server that provides interface to Google DeepMind's AlphaGenome genomics predictions API.

A proof-of-concept web application to streamline the design of fishing lures by leveraging Blenders Python API (MCP), Three.js previews, and custom AI pipelines. This tool replaces traditional hand-painting with automated texture application, multi-view rendering, and advanced scene simulations.

An MCP (Model Context Protocol) server that provides long-term memory capabilities for AI agents, enabling persistent storage, retrieval, and semantic search of contextual memories across sessions.

falcon-mcp is a Model Context Protocol (MCP) server that connects AI agents with the CrowdStrike Falcon platform, powering intelligent security analysis in your agentic workflows. It delivers programmatic access to essential security capabilitiesincluding detections, incidents, and behaviorsestablishing the foundation for advanced security operations and automation.

MCP server for integrating Actual Budget with Claude and other LLM assistants.

This project implements an agentic AI control server using a lightweight MCP (Multi-Agent Control Protocol) framework. It connects agents to powerful remote LLMs like OpenAI and Claude, and exposes an HTTP API for orchestrating tasks like planning, classification, code generation, and anomaly detection.

This SDK helps you build AI agents capable of auto-configuring other AI Agents and MCP Servers. It is based on Google's A2A.

The Universal_FSCompliance_MCP Project's mission is to enable Financial Institutions to slice through red tape and make it easier to bring the right financial products safely to consumers. The red tape is spawned by the worldwide compulsive urge to make rules, combined with the real-life knotweed nature of the rules. Compliance with the rules is simply impossible without an AI-native application.

A comprehensive Model Context Protocol (MCP) platform providing standardized integrations between AI assistants and various services and APIs. This repository contains both JavaScript and Python implementations of MCP servers and clients for seamless service integration.

RDKit MCP Server is an open-source MCP server that enables language models to interact with RDKit through natural language. The goal is to provide agent-level access to every function in RDKit 2025.3.1 without writing any code.

Generated on: 2025-07-14 03:52:46 UTC Current User: lllucius

A complete DuckLake semantic layer implementation with MinIO object storage, DuckDB analytics engine, and Cube.dev business semantics, providing an MCP (Model Context Protocol) server for agentic AI platforms.

This workspace provides a set of tools and demos for interacting with LLMs (Groq, Ollama), MCP tool servers, and n8n automation. It includes Python scripts, Streamlit apps, and server modules for math and weather tasks.

This project demonstrates how to extend GitHub Copilot capabilities using Python, Langchain, and the Model Context Protocol (MCP), allowing for more deterministic and powerful interactions with the LLM.

The contents of this repository are a collection of OpenUSD tools that interface with MCP (modelcontextprotocol) and A2A (agent2agent). The goal of this effort is to give large language models and agentic workflows the tools to work directly with OpenUSD objects, e.g., UsdStage, prims, hierarchies, and others and integrate them into comprehensive asset creation workflows.

A Python package that combines Google's Gemma language model with MCP (Model Content Protocol) server integration, enabling powerful function calling capabilities across both local functions and remote MCP tools.

Exposes tools for an LLM to parse a must-gather directory and find clusters that failed installation along with any relevant logs.

A Model Context Protocol (MCP) server that provides AI assistants with deep RStudio integration capabilities, including environment management, code execution, project management, and more.

MCP Server to support RAG-based Agentic Workflows related to Hockey Stats

Run + Intercept - A powerful Rust-based process manager that intelligently manages long-running processes with both AI assistant integration and command-line interface capabilities.

A Model Context Protocol (MCP) server that provides AI assistants with access to the latest Godot documentation, helping developers with Godot development by serving class documentation directly to LLMs.

A sophisticated Model Context Protocol (MCP) client application built with Meteor.js and React that provides intelligent tool selection and orchestration across multiple healthcare data systems. This application serves as a unified interface for Epic EHR, Aidbox FHIR, MongoDB Atlas and medical document processing systems.

I built this MCP server to access 2.4M+ arXiv papers directly in Claude Desktop. It uses GROBID for academic PDF extraction and builds citation networks to track research connections.

, LLM

A high-performance semantic code search tool for C# projects using the Model Context Protocol (MCP). Built with .NET 9 and optimized with AVX-512 SIMD acceleration.

MCP (Model Context Protocol) Server Community Registry - Discover and share high-quality MCP server projects

This project is a Streamlit-based web application that generates personalized learning paths using the Model Context Protocol (MCP). It integrates with various services including YouTube, Google Drive, and Notion to create comprehensive learning experiences.

MCP Chat is a command-line interface application that enables interactive chat capabilities with AI models through AWS Bedrock. The application supports document retrieval, command-based prompts, and extensible tool integrations via the MCP (Model Control Protocol) architecture.

An agent-based Retrieval-Augmented Generation (RAG) chatbot that answers user queries from uploaded documents using modular agents and the Model Communication Protocol (MCP). Supports multiple file formats and provides context-aware, intelligent responses.