Open-source alternatives to Magic Mcp

This project provides a translation layer and set of adapters designed to bridge AI agents with the Model Context Protocol. It functions as an integration layer that allows agents to operate as protocol-compliant servers and enables the conversion of protocol-based tools into formats compatible with agent frameworks and logic graphs. The adapters facilitate tool interoperability by wrapping external protocol tools for use within agent workflows and exposing internal agent capabilities to any client implementing the Model Context Protocol. This creates a communication bridge that supports inte

gluestack-ui is a cross-platform React component library built with Tailwind CSS. It provides over 30 pre-built, accessible components that can be installed by copying their source files directly into a project, giving developers full control over customization without external runtime dependencies. Every component implements WAI-ARIA patterns, keyboard navigation, and screen reader support out of the box. A key differentiator is the copy-paste architecture: rather than a traditional package dependency, component source code is placed in the project, allowing direct editing and eliminating ve

Coss is an accessible UI component library and design system framework used to build web interfaces. It provides a comprehensive kit of interactive elements and layout building blocks that follow screen reader and keyboard navigation standards. The project functions as a UI overlay management library, offering specialized tools for implementing anchored popovers, tooltips, and slide-out panels with smooth transitions. It includes a set of accessible form primitives and selection controls to ensure compatibility across different assistive technologies. Its broader capabilities cover the const

shadcn-svelte is a collection of accessible and customizable user interface elements for Svelte applications. Rather than being distributed as a traditional dependency, these components are provided as source code that is copied directly into the project codebase. The library utilizes a registry-based distribution system, allowing users to install specific UI blocks and components via a command-line interface. This system uses JSON metadata to define dependencies and file paths, while a bootstrapping process automates the configuration of styles and CSS variables. The project integrates Tail

Zag is a headless UI state machine library that provides unstyled component logic to ensure consistent behavior across different rendering engines. It functions as a toolkit for modeling complex user interface interactions using statecharts, decoupling the underlying logic and accessibility attributes from visual styling. The library is framework-agnostic, utilizing specialized adapters to bridge its state machine logic with various JavaScript libraries such as React, Solid, Vue, and Svelte. This approach allows developers to maintain a single interaction model while applying any CSS or styli

Yao is an LLM agent framework and low-code web app builder designed for orchestrating autonomous AI agents. It provides a platform to design, deploy, and coordinate agents with specialized personas that can plan tasks, utilize external tools, and execute multi-stage pipelines. The project distinguishes itself through a Model Context Protocol server for connecting assistants to external binaries and HTTP services, and a gRPC remote execution engine that allows agents to manage remote servers and devices. It includes a model-agnostic provider bridge that supports dynamic switching between vario

Polaris React is a production-ready component library that implements Shopify's Polaris design system for building consistent merchant-facing admin interfaces. It provides a comprehensive set of reusable React components, including accessible form inputs, data display elements, layout and navigation structures, and visual feedback indicators, all styled through a semantic color token system applied via CSS custom properties for dynamic light and dark mode support. The library distinguishes itself with an icon-first visual language featuring over 400 commerce-specific SVG icons delivered as fi

Open-UI is a set of web UI standard specifications and a standardized UI component library. It provides technical definitions for universal UI components, behaviors, and accessibility requirements designed to ensure cross-browser compatibility through a series of web language proposals. The project features a web accessibility polyfill and extensible control polyfills that provide modern UI control functionality in environments lacking native browser support. It includes a browser compatibility suite to verify that components meet defined behavioral and accessibility requirements. The librar

Cursive is a cross-platform terminal user interface toolkit and framework for building interactive applications in Rust. It provides a modular system for creating text-based graphical interfaces, utilizing a dedicated engine to manage the main display loop and view hierarchies. The toolkit features a backend-agnostic abstraction layer to ensure consistent rendering and input handling across different operating systems. It distinguishes itself through a palette-based theme engine that supports runtime theme loading and true color rendering, as well as the ability to generate user interface hie

Taiga UI is an Angular UI component library and accessible design system used for building enterprise web interfaces. It provides a comprehensive collection of reusable interface elements and layout tools, functioning as a mobile-first UI kit with responsive components that adapt to different device capabilities. The library distinguishes itself through an integrated data visualization library featuring various chart types and a dedicated form management framework with built-in validation and formatting for specialized data. It also features AI-driven development workflows by integrating comp

Argon Design System is a frontend template collection and UI component library built on Bootstrap 4 for rapid web application development and prototyping. It structures user interface elements into self-contained, reusable blocks that combine with pre-built page templates and stylesheet variable customization. The framework includes pre-styled views for credential authentication, password recovery, user registration, and profile creation layouts. It supports external identity provider integration and user session persistence alongside interactive JavaScript behaviors such as tooltips, modals,

This project is a Model Context Protocol server that enables large language models to generate and render data visualizations, charts, and diagrams. It functions as a toolset for AI assistants to transform raw data into professional visual representations. The server utilizes an intelligent selection layer to determine the most effective visualization format based on the provided data. It supports remote rendering via external HTTP services and provides the flexibility to route requests to self-hosted rendering endpoints for private network environments. Capabilities cover a wide range of da

This project is a Model Context Protocol server that provides large language models with neural web search and webpage content extraction capabilities. It implements a standardized interface to expose research tools and resources to compatible clients. The server integrates a neural search engine to retrieve real-time internet data using semantic embeddings rather than keyword matching. It includes specialized utilities for company intelligence and reasoning-based deep research, enabling the collection and synthesis of organizational data and professional profiles. The system covers a broad

mcp-go is a Go implementation of the Model Context Protocol (MCP) providing an SDK and framework for building servers that connect large language model applications to external tools and data sources. It serves as a developer kit for implementing bidirectional communication and structured data exchange between AI clients and servers. The framework enables the creation of executable tools with structured output schemas, reusable prompt templates, and data resource exposure via URI templates. It supports multiple transport layers, including stdio, HTTP, and Server-Sent Events, using a transport

ddgs is a metasearch engine and web content extractor that provides a toolkit for programmatically retrieving search results from DuckDuckGo. It functions as a search API server and a Model Context Protocol server to integrate web search capabilities directly into large language model environments. The project distinguishes itself by aggregating text, image, news, and video results from multiple providers into a single interface. It includes a utility for fetching URLs and converting HTML content into markdown, plain text, or structured data. The system covers a broad range of search capabil

This project is a browser automation toolset and Model Context Protocol server that connects large language models to live browser sessions. It provides a web debugging interface and a quality auditor to facilitate the analysis of document object model structures and browser logs. The system implements a bridge that streams diagnostics into AI-powered editors, allowing for the automated identification of web bugs. It features a data sanitization pipeline that removes cookies and sensitive headers to prevent private information leakage during the analysis process. The toolset covers a range o

The inspector is a diagnostic and validation tool for the Model Context Protocol. It provides an interactive interface and a transport proxy to discover, inspect, and execute the tools, prompts, and resources provided by an MCP server. The project serves as a debugger and compliance tester to verify that server implementations adhere to the protocol specification and JSON-RPC standards. It allows for real-time monitoring of message exchanges and logs between clients and servers across various transport layers, such as standard input/output and Server-Sent Events. The tool covers a broad rang

The project is a web tool and utility that translates natural language text prompts into fully functional user interface code using artificial intelligence language models. It functions as an artificial intelligence prompt customization tool and a React component code generator that streams and exports custom user interface elements. The software translates text prompts into user interface components through edge functions and supports multi-format code export. Users can convert generated interface code into preferred styling frameworks and component libraries to copy and paste ready-to-use

David AI is a UI development toolkit that combines AI-powered page generation with a library of pre-built, copy-paste-ready components built on Tailwind CSS. At its core, it offers an AI builder that can generate complete landing pages and dashboards from natural language prompts, outputting clean, responsive Tailwind CSS code. The project provides a comprehensive collection of UI components—including buttons, forms, navigation elements, and data displays—that can be assembled into full page sections like hero blocks, pricing tables, and dashboards. The toolkit distinguishes itself through a

Tailwind Starter Kit is a copy-paste UI component library built with Tailwind CSS, designed to accelerate front-end development by providing pre-built, reusable interface blocks that can be inserted directly into any project without package managers or build tools. It delivers identical UI components as native code for React, Vue, Angular, and plain HTML, making it a framework-agnostic resource for assembling responsive layouts. The kit structures its UI blocks as plain Tailwind markup that AI code generators can parse and reproduce from natural-language descriptions, making it compatible wit

Atmosphere is a Java-based framework for building and coordinating AI agents. It provides a real-time transport layer for streaming data via WebSockets, SSE, gRPC, and WebTransport, alongside a multi-agent orchestration framework for managing agent fleets through sequential, parallel, and graph-based execution workflows. The project features a durable workflow engine that persists agent state as snapshots, allowing long-running tasks to survive system restarts and incorporate human-in-the-loop approvals. It also implements Model Context Protocol servers to expose tools, resources, and prompt

TablePro is a cross-platform database management client designed for browsing, querying, and administering both SQL and NoSQL databases. It functions as a unified workspace that integrates a code-centric SQL editor with schema visualization tools, allowing developers to manage complex data models and execute queries across diverse database engines. The application distinguishes itself through an agentic AI integration layer that connects language models directly to database tools, enabling automated query generation, optimization, and error fixing with configurable approval gates. It features

mcp-feedback-enhanced is a human-in-the-loop orchestrator and feedback tool for the Model Context Protocol. It provides a graphical interface for reviewing and approving AI-driven operations to prevent automated execution errors, using a socket-based system to synchronize state between backend AI processes and a user-facing interface. The project distinguishes itself by supporting a cross-platform deployment model available via native desktop wrappers and web browsers. It includes environment-aware context detection to identify if the system is running locally, via SSH, or within WSL, allowin

This is a Figma MCP server that exposes document manipulation capabilities to AI assistants through the Model Context Protocol. It functions as a bridge between AI tools and Figma, enabling programmatic creation, reading, updating, and deletion of design elements including frames, text nodes, components, and connectors. The server provides AI-powered design generation that translates natural language prompts into complete UI screens and design elements within Figma. It includes a design annotation system for adding, updating, and retrieving markdown-supported annotations on nodes, along with

Koog is an LLM agent framework used to build autonomous entities that execute tool-based workflows. It utilizes a graph-based workflow engine to define agent behaviors and decision paths as a directed graph of nodes and edges. The framework distinguishes itself through a model provider orchestrator that enables dynamic switching, load balancing, and automatic fallbacks between different AI backends. It implements the Model Context Protocol to connect agents to remote tool servers and features a RAG memory system using vector embeddings to maintain long-term conversation context. The project

The BeeAI Framework is an LLM agent framework and multi-agent orchestration engine used to build autonomous agents that coordinate reasoning, tool execution, and complex workflows. It functions as a structured AI output controller and RAG integration library, providing a unified interface to manage multiple language model providers. The framework is distinguished by its implementation of the Model Context Protocol, allowing agents, tools, and models to be shared between different AI platforms and hosted as agentic tooling servers. It enables the design of collaborative agent teams through dec

superpowers-zh is a collection of tools designed to enhance AI coding agents through a workflow orchestrator, a prompt library for coding assistants, and a server framework for the Model Context Protocol. It provides a specialized set of technical prompts optimized for Chinese language environments and regional software development standards. The project distinguishes itself by offering localized coding prompt sets that apply regional technical documentation standards and code review cultures. It enables the deployment of prompt-based work methodologies and localized programming skills into A