Tuui
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
What is Tuui?
Tuui is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to desktop mcp client designed as a tool unitary utility integration, accelerating ai adoption through the model context protocol (mcp) and enabling cross-vendor llm api orchestration.
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A desktop MCP client designed as a tool unitary utility inte
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx tuuiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Tuui
Tuui is an open-source desktop MCP client designed as a unified tool integration layer that accelerates AI adoption by connecting multiple LLM providers through a single interface. It supports Claude, ChatGPT, DeepSeek, Qwen, and any OpenAI-compatible endpoint, and implements the full MCP specification including tools, prompts, resources, sampling, and elicitation. Developers use Tuui to evaluate different LLMs side-by-side, manage MCP server configurations, and build agentic workflows without being locked into a single AI vendor.
Prerequisites
- Node.js installed (required for NPX/Node-based MCP servers)
- Python and the uv package manager (required for UV/UVX-based MCP servers)
- Docker (required for Docker-based MCP servers)
- API keys for at least one LLM provider (Anthropic, OpenAI, or compatible)
- A supported operating system: Windows, Linux, or macOS
Download the Tuui desktop binary
Get the prebuilt binary for your platform from the Tuui GitHub releases page. Binaries are available for Windows, Linux, and macOS — no build step required for standard usage.
# Visit: https://github.com/AI-QL/tuui/releases/latest
# Download the binary for your OS and run it directlyConfigure an LLM provider
Edit the llm.json configuration file in the assets/config directory to point Tuui at your preferred LLM endpoint. The file accepts a single object or an array of provider objects.
{
"name": "Claude",
"apiKey": "sk-ant-your-key",
"url": "https://api.anthropic.com",
"path": "/v1/messages",
"model": "claude-opus-4-5",
"mcp": true
}Add MCP servers via mcp.json
Edit the mcp.json configuration file to register the MCP servers you want to use. Each entry follows the standard MCP server schema with command, args, and optional env fields.
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
}
}
}Launch Tuui and verify tool discovery
Open the Tuui application. It will automatically discover tools, prompts, and resources from your configured MCP servers. You should see the server list in the sidebar once connected.
Clear storage if configuration state is stale
Tuui stores runtime configuration in localStorage. If you encounter stale settings or unexpected behavior after changing your config files, clear storage via the tray menu option 'Clear Storage'.
Tuui Examples
Client configuration
Example llm.json entry for connecting Tuui to the Anthropic Claude API with MCP enabled.
{
"name": "Claude Sonnet",
"apiKey": "sk-ant-your-anthropic-key",
"url": "https://api.anthropic.com",
"path": "/v1/messages",
"model": "claude-sonnet-4-5",
"mcp": true
}Prompts to try
Example prompts to exercise Tuui's multi-provider and MCP tool integration capabilities.
- "List all MCP servers currently connected and show their available tools"
- "Use the filesystem server to read the contents of my project README"
- "Compare how Claude and a local Ollama model respond to the same coding question"
- "Run a prompt template from the connected MCP server's prompts resource"
- "Show me all resources available from the currently connected MCP servers"Troubleshooting Tuui
MCP servers fail to connect or tools are not discovered
Verify the correct runtime is installed: Node.js for npx-based servers, Python+uv for uvx-based servers, Docker for container-based servers. On macOS/Linux, check that CLI paths in mcp.json match your system's actual binary locations (use 'which npx' to confirm).
LLM responses fail or return authentication errors
Double-check the apiKey, url, and path values in llm.json. For Anthropic, the path should be '/v1/messages'. For OpenAI-compatible endpoints, '/v1/chat/completions'. Ensure the selected model name matches your provider's API model identifier.
Configuration changes are not taking effect after editing JSON files
Tuui caches configuration in localStorage. After editing config files, use the tray menu 'Clear Storage' option and restart the application to force a fresh load from your updated JSON files.
Frequently Asked Questions about Tuui
What is Tuui?
Tuui is a Model Context Protocol (MCP) server that desktop mcp client designed as a tool unitary utility integration, accelerating ai adoption through the model context protocol (mcp) and enabling cross-vendor llm api orchestration. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Tuui?
Follow the installation instructions on the Tuui GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Tuui?
Tuui works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Tuui free to use?
Yes, Tuui is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Tuui Alternatives — Similar Developer Tools Servers
Looking for alternatives to Tuui? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 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
★ 104.5kA 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
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA 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.
Set Up Tuui in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Tuui?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.