MCPgee
MCPgee
MCPgeeMCPgee

GGUI

v1.0.0•Developer Tools•stable

The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

agent-frameworkagent-uiagentsaigenerative-ui
Share:
16
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is GGUI?

GGUI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to universal interface layer between ai agents and humans. generate rich uis on demand via mcp.

The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The universal interface layer between AI agents and humans.

Use Cases

Generative UI generation via MCP
Rich AI-driven interfaces on demand
ggui-ai

Maintainer

LicenseApache-2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx ggui

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use GGUI

GGUI is a generative UI framework and MCP server that acts as the interface layer between AI agents and human users, enabling agents to render rich, interactive UIs on demand during conversations. Using the ggui_render tool, an AI agent can create forms, dashboards, tables, and other UI components that appear in a session viewer, collect user input via clicks and form submissions, and update components in real time. This closes the feedback loop between AI agents and humans without requiring hard-coded frontend code.

Prerequisites

  • Node.js 18+ and npm or pnpm installed
  • An Anthropic API key (ANTHROPIC_API_KEY) or OpenAI API key for LLM-powered generation
  • The GGUI CLI installed globally: npm install -g @ggui-ai/cli
  • An MCP client such as Claude Desktop or Cursor that supports tool-use
  • A browser to view the GGUI session viewer (served locally on port 6781 by default)
1

Install the GGUI CLI

Install the GGUI CLI globally using npm. This provides the 'ggui' command for serving the MCP server and session viewer.

npm install -g @ggui-ai/cli
2

Start the GGUI MCP server

Run 'ggui serve' to start the MCP server and the session viewer. The MCP endpoint is exposed at http://127.0.0.1:6781/mcp and the viewer opens in your browser automatically.

ANTHROPIC_API_KEY=sk-ant-... ggui serve
3

Configure your MCP client

Add GGUI to your MCP client's configuration pointing to the running local server's HTTP MCP endpoint.

{
  "mcpServers": {
    "ggui": {
      "url": "http://127.0.0.1:6781/mcp"
    }
  }
}
4

Let an AI agent render a UI

Prompt your AI assistant to render a UI for a task. The agent will call ggui_render with a natural-language description and data, and the resulting interface will appear in the GGUI session viewer in your browser.

5

Collect user input from the UI

The agent can call ggui_consume to long-poll for user gestures (button clicks, form submissions) from the rendered UI. The user interacts in the browser and the agent receives the response to continue the workflow.

GGUI Examples

Client configuration

MCP client configuration connecting to a locally running GGUI server.

{
  "mcpServers": {
    "ggui": {
      "url": "http://127.0.0.1:6781/mcp"
    }
  }
}

Prompts to try

Example prompts that trigger GGUI to render interactive UIs during AI conversations.

- "Render a form for me to fill in my contact details (name, email, phone) and wait for my submission."
- "Show me a table UI with these 5 products and their prices, and let me select which ones to order."
- "Create a dashboard UI showing these sales metrics as a summary card and wait for me to click 'Export'."
- "Render a yes/no confirmation dialog asking if I want to proceed with deleting 47 records."

Troubleshooting GGUI

The session viewer does not open or shows a blank page

Verify that 'ggui serve' started successfully and is listening on port 6781. Check the terminal for startup errors. Navigate manually to http://localhost:6890 (the dev viewer port) or http://127.0.0.1:6781 to see if the server is responding.

The MCP client cannot connect to the GGUI endpoint

Ensure the GGUI server is running before starting your MCP client. The URL in the config must match exactly: http://127.0.0.1:6781/mcp. Check that no other service is occupying port 6781.

ggui_render fails with API key errors

Set the ANTHROPIC_API_KEY environment variable before running 'ggui serve'. If using OpenAI instead, set OPENAI_API_KEY. The API key must be valid and have sufficient quota for the generation requests.

Frequently Asked Questions about GGUI

What is GGUI?

GGUI is a Model Context Protocol (MCP) server that universal interface layer between ai agents and humans. generate rich uis on demand via mcp. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install GGUI?

Follow the installation instructions on the GGUI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with GGUI?

GGUI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is GGUI free to use?

Yes, GGUI is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

GGUI Alternatives — Similar Developer Tools Servers

Looking for alternatives to GGUI? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "ggui": { "command": "npx", "args": ["-y", "ggui"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use GGUI?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides