Gemini CLI Desktop
Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
What is Gemini CLI Desktop?
Gemini CLI Desktop is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to web/desktop ui for gemini cli/qwen code. manage projects, switch between tools, search across past conversations, and manage mcp servers, all from one multilingual interface, locally or remotely.
Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, sw
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx gemini-cli-desktopConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Gemini CLI Desktop
Gemini CLI Desktop is a cross-platform web and desktop application that provides a graphical user interface for Gemini CLI and Qwen Code, letting developers manage AI coding sessions, switch between models, search conversation history, and configure MCP servers all from one multilingual interface. It supports Gemini 2.5 Pro/Flash, Gemini 3 Pro/Flash, Qwen Code, and custom OpenAI-compatible providers, and runs as either a local desktop app or a self-hosted web service. Teams use it to get a visual layer on top of Gemini CLI without giving up the power of MCP tool integrations.
Prerequisites
- A Gemini API key from Google AI Studio (aistudio.google.com)
- For pre-built binaries: no additional dependencies (download from GitHub Releases)
- For building from source: Rust, Node.js, pnpm, and the just task runner
- On Linux from source: libgdk-pixbuf-2.0-dev, libpango1.0-dev, libwebkit2gtk-4.1-dev, and related GTK libraries
Download the pre-built binary for your platform
Go to the GitHub Releases page and download the installer for your OS: Windows (x64 .exe), macOS (Intel or Apple Silicon .dmg), or Linux (x64 AppImage).
https://github.com/Piebald-AI/gemini-cli-desktop/releasesInstall and launch the application
Run the installer or mount the .dmg (macOS), mark the AppImage as executable on Linux, or run the .exe on Windows. The app starts a local backend on port 1858 and opens the web UI.
# Linux AppImage example:
chmod +x gemini-cli-desktop.AppImage
./gemini-cli-desktop.AppImageEnter your Gemini API key
On first launch, the application will prompt you for a Gemini API key. Get one from https://aistudio.google.com/app/apikey and paste it into the settings screen.
Select your model
Use the model switcher in the interface to choose from Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 3 Pro, Qwen Code, or a custom OpenAI-compatible provider endpoint.
Configure MCP servers from the UI
Open the MCP Servers section in settings to add, remove, or toggle MCP server integrations. The UI writes the same JSON config that Gemini CLI uses natively.
(Optional) Build from source
Clone the repo and use the just task runner to build all targets including the desktop app and web frontend.
git clone https://github.com/Piebald-AI/gemini-cli-desktop
cd gemini-cli-desktop
just deps build-allGemini CLI Desktop Examples
Client configuration
Gemini CLI Desktop manages its own MCP server settings through the UI. If you need to manually edit the underlying Gemini CLI config, it follows this format:
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["-y", "my-mcp-package"]
}
}
}Prompts to try
Example tasks you can accomplish inside Gemini CLI Desktop using Gemini models and connected MCP tools.
- "Search my conversation history for all sessions where we discussed database migrations"
- "Switch to Gemini 2.5 Flash and summarize the last 3 conversations in this project"
- "Use the file system MCP tool to read my package.json and suggest dependency updates"
- "Start a new project session for my API refactoring work and set the context"
- "Show me all MCP servers currently configured and which ones are active"Troubleshooting Gemini CLI Desktop
Application fails to start or the web UI does not open
Check that port 1858 is not occupied by another process. On Linux, ensure all required GTK libraries are installed (libwebkit2gtk-4.1-dev, libgdk-pixbuf-2.0-dev). Run from a terminal to see startup error messages.
Gemini API requests fail with authentication errors
Verify your API key is entered correctly in Settings. Keys must be from Google AI Studio (aistudio.google.com) and have the Generative Language API enabled. If the key was created in Google Cloud Console, ensure the correct project and API are activated.
MCP server shows as connected but tools are not available
Open the MCP Servers panel and check the server status indicator. Restart the MCP server from the UI, and verify the command or URL in the server configuration is reachable. Check the application logs in the terminal for connection errors.
Frequently Asked Questions about Gemini CLI Desktop
What is Gemini CLI Desktop?
Gemini CLI Desktop is a Model Context Protocol (MCP) server that web/desktop ui for gemini cli/qwen code. manage projects, switch between tools, search across past conversations, and manage mcp servers, all from one multilingual interface, locally or remotely. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Gemini CLI Desktop?
Follow the installation instructions on the Gemini CLI Desktop GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Gemini CLI Desktop?
Gemini CLI Desktop works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Gemini CLI Desktop free to use?
Yes, Gemini CLI Desktop is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Gemini CLI Desktop Alternatives — Similar Developer Tools Servers
Looking for alternatives to Gemini CLI Desktop? 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 Gemini CLI Desktop 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 Gemini CLI Desktop?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.