Gemini Desktop
The MCP Gemini Electron App is a cross-platform desktop application that creates a seamless chat interface for Google's Gemini AI models with extensible capabilities through a Model Context Protocol (MCP) framework.
What is Gemini Desktop?
Gemini Desktop is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp gemini electron app is a cross-platform desktop application that creates a seamless chat interface for google's gemini ai models with extensible capabilities through a model context protocol (mcp)...
The MCP Gemini Electron App is a cross-platform desktop application that creates a seamless chat interface for Google's Gemini AI models with extensible capabilities through a Model Context Protocol (MCP) framework.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The MCP Gemini Electron App is a cross-platform desktop appl
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx gemini-desktopConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Gemini Desktop
Gemini Desktop is a cross-platform Electron application that provides a native chat interface for Google's Gemini AI models, extended through the Model Context Protocol (MCP). It connects a Python backend to an Electron frontend, giving users a desktop-native experience with Gemini 1.5 Flash, 1.5 Pro, 2.5 Pro, and other models. The MCP layer lets you plug in additional servers — both Python-based (via file path) and Node.js-based (via JSON config) — so the AI can interact with external tools while chatting, with visual feedback on each tool call's success or failure.
Prerequisites
- Python 3.9 or later with pip and the uv package manager installed
- Node.js 16 or later and npm installed for the Electron frontend
- A Google AI Studio account and a valid GOOGLE_API_KEY
- Git to clone the repository
- An MCP-compatible client or the bundled Electron app
Clone the repository
Download the source code from GitHub to your local machine.
git clone https://github.com/kkrishnan90/gemini-desktop.git
cd gemini-desktopSet your Google API key
Obtain a free API key from Google AI Studio (aistudio.google.com) and export it as an environment variable before starting the backend.
export GOOGLE_API_KEY=your_api_key_hereInstall and start the Python backend
The backend handles all Gemini API calls and MCP tool routing. Install dependencies with uv and start the server.
cd python_backend
pip install uv
uv pip install .
python main.pyInstall and start the Electron frontend
In a separate terminal, install npm dependencies and launch the desktop app.
cd mcp-gemini-desktop
npm install
npm startSelect a Gemini model
Inside the running app, open the Settings dialog and choose your preferred model — Gemini 1.5 Flash, 1.5 Pro, or 2.5 Pro Exp — depending on your task and quota.
Connect additional MCP servers
Use the MCP configuration panel in the app to add Python-based servers by file path or Node.js-based servers via JSON. Example servers (calculator, weather) are included under mcp-gemini-desktop/mcp_example_servers/.
Gemini Desktop Examples
Client configuration
The app manages its own MCP server list through the UI, but you can also describe a stdio-based server in JSON format when prompted.
{
"mcpServers": {
"gemini-desktop": {
"command": "python",
"args": ["/path/to/gemini-desktop/python_backend/main.py"],
"env": {
"GOOGLE_API_KEY": "your_api_key_here"
}
}
}
}Prompts to try
Prompts that showcase Gemini capabilities alongside connected MCP tools.
- "Summarize the latest news about large language models"
- "What is 2456 multiplied by 37? Use the calculator tool"
- "What is the weather in Tokyo right now?"
- "Explain the difference between Gemini 1.5 Pro and 2.5 Pro"
- "Help me write a Python script to parse a CSV file"Troubleshooting Gemini Desktop
Backend fails to start with 'GOOGLE_API_KEY not set'
Make sure you have exported the GOOGLE_API_KEY environment variable in the same shell session before running 'python main.py'. On Windows use 'set GOOGLE_API_KEY=your_key'.
Electron app shows a blank window or fails to connect to backend
Confirm the Python backend is running and listening before starting the Electron app. Check the terminal running 'python main.py' for errors or port conflicts.
An MCP tool call shows 'failed' in the UI
Check that the MCP server process is running and the path or command you entered in the settings is correct. Python servers need the full absolute file path; Node.js servers need npm packages installed globally or via npx.
Frequently Asked Questions about Gemini Desktop
What is Gemini Desktop?
Gemini Desktop is a Model Context Protocol (MCP) server that mcp gemini electron app is a cross-platform desktop application that creates a seamless chat interface for google's gemini ai models with extensible capabilities through a model context protocol (mcp) framework. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Gemini Desktop?
Follow the installation instructions on the Gemini Desktop GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Gemini Desktop?
Gemini Desktop works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Gemini Desktop free to use?
Yes, Gemini Desktop is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Gemini Desktop Alternatives — Similar Developer Tools Servers
Looking for alternatives to Gemini 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 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 Desktop?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.