MCP Servers · AI-QL

tuui

TUUI is a desktop application that acts as a local client for the Model Context Protocol (MCP), enabling users to integrate and orchestrate multiple LLM APIs (ChatGPT, Claude, Qwen, etc.) without requiring external accounts. Built in TypeScript with Vue3, it runs on Windows, macOS, and Linux, supporting MCP tools, prompts, resources, sampling, and discovery features.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/AI-QL/tuui

1.2k

GitHub stars

105

Forks

TypeScript

Primary language

Apache-2.0

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	AI-QL/tuui
Owner	AI-QL
Primary language	TypeScript
License	Apache-2.0 — OSI-approved
Stars	1.2k
Forks	105
Open issues	2
Latest release	v1.5.1 (2026-05-14)
Last updated	2026-05-14
Source	https://github.com/AI-QL/tuui

What tuui is

A TypeScript/Electron-based MCP client with Vue3 frontend and Pinia state management, supporting cross-vendor LLM API orchestration via configurable JSON endpoints. Implements MCP specification for tools, prompts, resources, sampling, and elicitation; supports NPM/Node, Python/UV, and Docker-based MCP servers; includes MCPB (MCP Bundles) and remote MCP server support via mcp-remote.

Quickstart

Get the tuui source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/AI-QL/tuui.git2cd tuui3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Local AI Development & Experimentation

Teams needing a unified sandbox for testing multiple LLM providers and MCP integrations without cloud dependencies or per-request billing. Useful for rapid prototyping of AI-powered features before production deployment.

MCP Server Integration & Testing

Organizations building or deploying MCP servers who need a lightweight client to test tools, prompts, resources, and sampling features locally. Includes MCP server discovery and MCPB support for bundled extensions.

Multi-Vendor LLM Orchestration

Enterprises running heterogeneous LLM stacks (OpenAI, Anthropic, Alibaba Qwen, DeepInfra, self-hosted) requiring dynamic switching and failover configuration without application code changes.

Implementation considerations

Requires pre-existing LLM backend (ChatGPT, Claude, Qwen, or self-hosted) with API credentials; TUUI is a client only, not a model provider.
MCP server execution depends on runtime availability: Node.js for NPX/Node-based servers, Python+UV for Python-based, Docker for containerized servers; verify all dependencies before deployment.
Configuration stored in localStorage by default; no built-in encryption for API keys. Consider environment security posture and whether to use proxy/remote MCP servers for credential isolation.
Cross-platform support (Windows, macOS, Linux) but README indicates unresolved MCP spawn issues on macOS; test thoroughly on target OS before rollout.
Project marked as AI-generated with strict linting applied; review code for functional correctness and security before integrating into mission-critical pipelines.

When to avoid it — and what to weigh

Production Chatbot Deployment — TUUI is designed as a local development tool, not a scalable production deployment. For customer-facing applications, use hosted LLM platforms or dedicated inference infrastructure.
Strict Security/Compliance Requirements — Desktop applications storing API keys and credentials in localStorage present elevated risk. Organizations with SOC2, HIPAA, or similar mandates should use enterprise-grade deployments with centralized secrets management.
Headless/Server-Side Integration — TUUI is Electron-based (GUI-first). If you need a CLI tool, programmatic SDK, or server-side integration without UI, consider the MCP SDK directly or alternative tooling.
Large-Scale Data Processing — No indication of optimization for batch processing, streaming large documents, or handling concurrent requests at scale. Better suited for interactive, single-user workflows.

License & commercial use

Licensed under Apache License 2.0 (Apache-2.0), a permissive OSI-approved license allowing commercial use, modification, and distribution with attribution and liability disclaimer.

Apache-2.0 permits commercial use, including proprietary modifications and closed-source derivative products, provided the original license and copyright notices are retained. No per-seat licensing or commercial restrictions apply. However, this is a development tool; ensure your LLM API subscriptions (OpenAI, Anthropic, etc.) comply with their own terms. Use in commercial products should be reviewed against your LLM provider's ToS.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Adequate
License clarity	Clear
Deployment complexity	Moderate
DEV.co fit	Good
Assessment confidence	High

Security considerations

TUUI stores API keys and LLM credentials in browser localStorage, which is unencrypted and accessible to any code in the application context. No built-in secrets rotation, audit logging, or multi-user access controls. Desktop application reduces public-facing attack surface but increases local compromise risk. For sensitive use, consider: (1) using proxy/remote MCP servers to isolate credentials, (2) running in isolated VM/container, (3) environmental secret management external to TUUI. Verify that all MCP server code (especially user-installed ones) is trustworthy. No security audit or CVE history mentioned.

Alternatives to consider

OpenAI Playground / Claude Console

First-party hosted web interfaces with built-in LLM access; simpler for single-vendor workflows but no MCP or cross-vendor orchestration.

Langchain / LlamaIndex

Python/JavaScript SDKs for programmatic LLM/MCP integration with more flexible deployment (CLI, API, cloud); steeper learning curve but better for production pipelines.

Continue.dev / Codeium IDE Extensions

IDE-native AI assistants with some MCP support; tightly coupled to editor but simpler for developers focused on code generation rather than general-purpose orchestration.

Software development agency

Build on tuui with DEV.co software developers

Download TUUI today or review our AI development services to integrate MCP and multi-vendor LLM orchestration into your products.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

MAI-UI mcp-client-cli mcp-ui

Related on DEV.co

Explore the category and the services that help you build with it.

MCP Servers AI Development API Development Talk to DEV.co

tuui FAQ

Do I need an OpenAI account to use TUUI?

No. TUUI is account-agnostic. You provide your own LLM API endpoints and credentials (OpenAI, Claude, Qwen, DeepInfra, self-hosted, etc.). You still need accounts/subscriptions with your chosen LLM provider.

Can I use TUUI as a backend service for my web app?

Not directly. TUUI is a desktop GUI application (Electron-based). For server-side integration, use the MCP SDK or a dedicated API wrapper. You could theoretically expose TUUI over a network, but that is unsupported and not secure.

What happens if an MCP server command (e.g., `npx`, `uv`) is not available?

TUUI will fail to initialize that MCP server with a spawn error. Install the required runtime (Node.js, Python+UV, Docker) on your system and ensure the command is in your PATH. Use absolute paths as a workaround per the README.

Is my data private in TUUI?

API keys and chat history are stored locally in your application; they are not uploaded to Devco servers. However, the actual LLM requests are sent to your configured LLM provider (OpenAI, Anthropic, etc.), which follows their privacy policies. MCP servers can also process local files; review their behavior.

Software developers & web developers for hire

DEV.co is a software development agency delivering custom software development services to companies building on open source. Our software developers and web developers design, integrate, and ship production systems — spanning web development, APIs, AI, data, and cloud. If tuui is part of your mcp servers roadmap, our team can implement, customize, migrate, and maintain it.

Ready to Unify Your LLM Workflow?

Download TUUI today or review our AI development services to integrate MCP and multi-vendor LLM orchestration into your products.

Talk to DEV.co Schedule a Consultation