AI 機器學習 資源

Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations and evals. You can run Mastra on your local machine, or deploy to a serverless cloud.

React + TypeScript + Vite , Model Context Protocol(MCP) AI .

(Lark)MCP Function Call AI Agent

**A hiring assistant that uses the MCP (Model Context Protocol) with fastAPIMCP

A Python-based, context-aware AI system that fetches real-time US weather alerts using the NOAA/NWS API, shares information using a Model Context Protocol (MCP), and generates natural-language responses using the GROQ LLM all without classes!

Scalable, high performance knowledge graph memory system with semantic retrieval, contextual recall, and temporal awareness. Provides any LLM client that supports the model context protocol (e.g., Claude Desktop, Cursor, Github Copilot) with resilient, adaptive, and persistent long-term ontological memory.

A simple Model Context Protocol (MCP) server for querying New Relic logs using NRQL queries. This server enables Large Language Models (LLMs) like Claude to interact with your New Relic data.

adb-mcp is a proof of concept project to create AI Agent for Adobe tools (Adobe Photoshop and Adobe Premiere) by providing an interface to LLMs via the MCP protocol.

A powerful Model Context Protocol (MCP) implementation for visualizing and analyzing directory structures. Why? Now you can let AI assistants understand and navigate your project structure efficiently, enabling smarter code navigation and project organization insights.

This repository is a proof of concept for implementing a Model Context Protocol (MCP) client using Gradio. It demonstrates how to interact with MCP servers using both STDIO and SSE communication methods within a Gradio interface.

A curated list of awesome Agent2Agent (A2A) protocol servers. This repository collects and organizes A2A-compliant server implementations to help developers build interoperable AI agent systems.

Local MCP Manager is a desktop application designed to simplify managing Model Context Protocol (MCP) servers. If you use multiple AI coding assistants or tools that rely on MCP (like Cursor, VS Code extensions, Claude Desktop, etc.), this application helps you configure and control them all from one place, avoiding repetitive setup in each tool.

This is a locally hosted Chatbot with MCP integrated.

A tiny command-line interface chat application that brings AI conversations to your terminal.

Welcome to the Learn Agentic AI repository! This project focuses on exploring Agentic AI through the Dapr Agentic Cloud Ascent (DACA) design pattern. We utilize various cutting-edge technologies, including the OpenAI Agents SDK, memory management, and cloud-native solutions.

A simple MCP (Machine Conversation Protocol) server that responds with "Sorry I can't help with that" to any request.

This project enables Claude to use Model Context Protocol (MCP) servers for enhanced capabilities, including web search, GitHub integration, file operations, database access, and communication tools.

A web-based graphical interface for AI chat interactions with support for multiple AI models and powerful MCP (Model Context Protocol) integrations. Beyond standard chat capabilities, y-gui leverages MCP to connect with Gmail, Google Calendar, image generation services, and more.

SelectorPlus LangGraph Project Setup This guide will walk you through the steps to set up and run the SelectorPlus LangGraph project.

(Pre-req - need to have Ollama installed, just and uv) for setting up - "just setup" for runnning - "just run"

This repo is part of the Panaversity Certified Agentic & Robotic AI Engineer program. It covers AI-201, AI-202 and AI-301 courses.

Connect Blender, CSM.ai and LLMs via the Model Context Protocol (MCP). This integration enables text and image based editing capabilities in Blender.

A Model Context Protocol (MCP) server for performing Kafka client operations from AI assistants.

MCPMan orchestrates interactions between LLMs and Model Context Protocol (MCP) servers, making it easy to create powerful agentic workflows.

Evo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI models and services.

A service that generates Cornell-style to your Notion summaries from text or URLs, using AI for content analysis and organization.

Endpoint: https://mcp.thetradeagent.ai/sse Mode: Remote-only (no local deployment required)

A simple chat UI for interacting with the GitMCP (GitHub Model Context Protocol) tools with optional Ollama backend for AI assistance.

Mode Choice Predictor for Traffic Models

This is an (unofficial) MCP server to let LLM clients interact with Figma's plugin API.

I'm impressed by OpenAI deep research, but it's very limited. This is my MCP version of deep research with more extendability and customization. I tried

This project exposes LogAI functionality as an MCP (Model Context Protocol) server for use with Claude desktop.

An open-source AI chatbot app powered by Model Context Protocol (MCP), built with Next.js and the AI SDK by Vercel.

A flexible Model Context Protocol (MCP) proxy that enables discovery and execution of tools across multiple MCP servers and JavaScript functions. Enabling to have a reduced context event if you have houndreds of tools. This mcp act as wrapper of other mcps (or libraries) doing a kind of Local RAG (Retrieval Augmented Generation) to reduce the context size providing the llm with 2 methods (discover and execute) and asking the llm to be concise about discovery. The execute method is a simple proxy

Welcome to AgentVault, an open-source toolkit designed for secure and decentralized AI agent interoperability. This repository includes a Python library, a Registry API, and a Command Line Interface (CLI) that enable seamless communication between AI agents using A2A (Agent-to-Agent) and MCP (Multi-Channel Protocol).

Scalable, high performance knowledge graph memory system with semantic retrieval, contextual recall, and temporal awareness. Provides any LLM client that supports the model context protocol (e.g., Claude Desktop, Cursor, Github Copilot) with resilient, adaptive, and persistent long-term ontological memory.

An experimental collection of MCP servers to help AI agents fetch enterprise data from Databricks, automate common developer actions on Databricks, etc:

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.

The Paystack Model Context Protocol (MCP) server allows AI agents to interact with Paystack through standardized MCP clients via tool calling. This protocol supports various tools to interact with different Paystack services.

This directory contains a Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files. It was created to overcome a limitation with Cursor. As of version 0.48.9, in Agent mode, the model could not edit notebooks or notebook cells in response to dialog in the AI chat pane. This provides the agent with a suite of MCP tools that allow direct notebook cell manipulation.

Welcome to the MCP Security Checklist repository! This project offers a comprehensive security checklist designed specifically for MCP-based AI tools. Created by SlowMist, our goal is to help safeguard the LLM plugin ecosystems.

MCP, model context protocol

Claudesidian MCP is an Obsidian plugin that enables AI assistants to interact with your vault through the Model Context Protocol (MCP). It provides atomic operations for vault management and implements a structured memory system. The plugin uses an Agent-Mode Architecture that organizes functionality into logical domains (agents) with specific operations (modes) within each domain.

This project is a cutting-edge AI-driven appointment booking system designed for agencies to schedule appointments, and manage queues in real-time efficiently. With AI Chat Bots, Retrieval-Augmented Generation (RAG), and MCP Client/Server integration, the system enables context-aware decision-making using external knowledge sources.

mcpport A lightweight gateway & registry for Model Context Protocol (MCP), enabling standardized connectivity for AI applications.

HWP-MCP (HWP) Claude AI Model Context Protocol(MCP) . , , AI .

A server that allows you to connect to MCP (Model Context Protocol) servers and OpenAPI servers and use them as plugins in LobeChat.

This library allows you connect your OpenAI models to mcp.run and expose your installed servlets as tools which can be invoked in process (without spinning up many server processes).

Thinking...

A biomedical literature annotation and relationship mining server based on PubTator3, providing convenient access through the MCP interface.

PydanticAI now includes support for MCP servers, use that instead

Spring AI 1.0.0-M7 Java mcp-client stdio HTTP SSEServer-Sent Events MCP Server

This project is developed by REER, INC. and made public for the community to use and test. We welcome contributors to help improve and expand the functionality of RhinoMCP. RhinoMCP connects Rhino, Grasshopper and more to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Rhino. This integration enables prompt-assisted 3D modeling, scene creation, and manipulation. (inspired by blender_mcp)

MCP OpenAI API Model Context Protocol OpenAI

A TypeScript implementation of a Model Context Protocol (MCP) client for LLM agents.

A Model Context Protocol (MCP) server for the Perplexity API written in Go. This server enables AI assistants like Claude (Code and Desktop) and Cursor to seamlessly access Perplexity's powerful search and reasoning capabilities directly from their interfaces.