gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
Gemini CLI is an open-source terminal agent that provides command-line access to Google's Gemini AI models directly from your development environment. Built for developers who prefer working in the terminal, it offers free-tier access with 60 requests per minute, supports Gemini 3 models with 1 million token context windows, and includes built-in tools for file operations, shell commands, Google Search grounding, and web fetching. The MCP server extends functionality through custom integrations and supports both interactive sessions and non-interactive scripting modes for workflow automation.
Key Features
Use Cases
- 01Query and edit large codebases with natural language understanding and code generation
- 02Generate new applications from PDFs, images, or sketches using multimodal input capabilities
- 03Automate pull request reviews and issue triage with GitHub Action integration
- 04Debug and troubleshoot code issues using conversational AI assistance in the terminal
- 05Automate operational tasks like querying repositories or handling complex Git rebases
- 06Build custom workflow automation with headless mode and structured JSON output
Related MCP Servers
View morepublic-apis
A collective list of free APIs
awesome-python
The definitive list that answers "I want to do X in Python, which tool should I use?"
awesome-selfhosted
A list of Free Software network services and web applications which can be hosted on your own servers
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
gemini-cli — FAQ
What is Gemini CLI MCP server?+
Gemini CLI is an open-source terminal agent that brings Google's Gemini AI models directly into your command line. It provides developers with conversational AI capabilities for code understanding, generation, debugging, and workflow automation, all accessible from the terminal.
How do I install Gemini CLI?+
You can install Gemini CLI using npx without installation (npx @google/gemini-cli), globally via npm (npm install -g @google/gemini-cli), through Homebrew on macOS/Linux (brew install gemini-cli), or via MacPorts and Anaconda. Multiple release channels are available including stable, preview, and nightly builds.
Do I need an API key to use Gemini CLI?+
Not necessarily. You can authenticate using OAuth by signing in with your Google account (no API key required), use a Gemini API key from AI Studio, or configure Vertex AI credentials for enterprise use. The OAuth option provides a free tier with 60 requests per minute and 1,000 requests per day.
Is Gemini CLI free to use?+
Yes, Gemini CLI offers a free tier when using OAuth authentication with a personal Google account, providing 60 requests per minute and 1,000 requests per day. The Gemini API key option also offers 1,000 free requests per day. Enterprise Vertex AI access requires a billing account.
Which AI clients work with Gemini CLI MCP server?+
Gemini CLI supports Model Context Protocol (MCP) integration, allowing it to work with MCP-compatible clients and extend functionality through custom MCP servers configured in the settings file. It can also be integrated into GitHub workflows via the Gemini CLI GitHub Action.
Can I use Gemini CLI in scripts and automation workflows?+
Yes, Gemini CLI supports non-interactive headless mode for scripting with multiple output formats including plain text, JSON, and stream-JSON for real-time event monitoring. This enables integration into CI/CD pipelines, automated workflows, and custom development tools.
How do I install gemini-cli?+
Open the source repository on GitHub and follow its README. gemini-cli is a mcp server — MCP Agents Market links you directly to the official repo.
Is gemini-cli free?+
gemini-cli is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.