mcp-ui

UI SDK based on the MCP protocol for building next-generation UI experiences.

MCPDevOpen source

Type: MCP
Transport: http
Open source: Yes
GitHub Stars: ★ 4.9k
Source: mcp-github
Repository: github.com/MCP-UI-Org/mcp-ui

Overview

mcp-ui is an SDK that implements the MCP Apps standard, providing rich web interfaces via the MCP protocol. It consists of two main packages: `@mcp-ui/server` and `@mcp-ui/client`, used for creating and rendering UI resources respectively. mcp-ui enables AI tools to interact with users through the MCP protocol, offering robust UI support. Ideal for developers who need to provide rich interfaces for AI tools.

Capabilities

▪Create UI resources
▪Register tools and resources
▪Render tool UI
▪Support multiple languages (TypeScript, Ruby, Python)

Use cases

Create interactive interfaces for AI toolsIntegrate UI functionality into MCP appsDevelop UIs with multi-language support

Setup

Requires: Node 环境API Key

npm install @mcp-ui/server @mcp-ui/client

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Supports TypeScript, Ruby, and Python.

mcp-ui supports which languages?

Use the `createUIResource` function to create UI resources.

How do I create a UI resource?

Related skills

gemini-cli

Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.

MCP

private-gpt

Provides a complete API layer for local models, supporting RAG, skills, tools, and more.

MCP

planning-with-files

File-based persistent planning skill, ideal for AI coding agents and long-running tasks.

Agent Skill

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP