An MCP server that connects AI assistants like Claude to Google Gemini CLI for large file analysis and codebase understanding.
Gemini MCP Tool is a Model Context Protocol (MCP) server that allows AI assistants like Claude to interact with the Google Gemini CLI. It solves the problem of analyzing large files and codebases by giving AI assistants access to Gemini's massive token window for deep analysis through natural language prompts.
Developers and technical users who work with AI assistants like Claude and need to analyze large codebases, files, or directories using Google Gemini's capabilities.
It uniquely bridges Claude and Gemini, allowing users to leverage Gemini's powerful analysis features directly within their preferred AI assistant workflow, saving tokens and enabling more complex file analysis than typical AI assistants can handle alone.
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
Provides AI assistants with seamless access to Gemini's analysis through the official CLI, enabling tools like Claude to leverage Gemini's capabilities without manual intervention, as shown in the one-line setup with npx.
Uses Gemini's massive token window to process entire codebases and large files via the @ syntax, demonstrated in examples like analyzing @src/main.js or summarizing @. directories.
Integrates Gemini's sandbox mode for isolated code testing, allowing users to safely run and debug scripts through AI prompts, such as testing @script.py or creating Python scripts.
Offers convenient slash commands like /analyze and /sandbox in Claude Code, making it easy to interact with Gemini directly from the AI assistant interface, though compatibility with other clients is untested.
The README explicitly states compatibility with other MCP clients has not been tested, making it primarily useful for Claude Code users and potentially unreliable in broader ecosystems.
Requires installing Node.js, the Gemini CLI, and configuring MCP servers across multiple steps, adding dependency overhead compared to simpler AI tool integrations or direct API usage.
Relies on the stability and updates of both the Gemini CLI and the MCP protocol, introducing risk of breakage from changes outside the project's control, with no built-in fallbacks.
Twitter scraper API skill for tweet search, advanced Twitter search, profile tweets, follower export, media download, monitors, webhooks, MCP, and posting automation: send tweets and replies.
The Gemini CLI confirmed that the MCP server built with Google Apps Script (GAS), a low-code platform, offers immense possibilities. If you've created snippets for GAS, these could be revitalized and/or leveraged in new ways by using them as the MCP server. The Gemini CLI and other MCP clients will be useful in achieving this.
MCP Gemini CLI is a Model Context Protocol server that wraps Google's Gemini CLI, allowing AI assistants like Claude to interact with Gemini's powerful features through a standardized protocol. It bridges the gap between AI assistants and Gemini's capabilities, enabling seamless integration of search, conversation, and multimodal analysis. ## Key Features - **Google Search** — Performs web searches through Gemini CLI with customizable result limits and model selection - **Chat Interface** — Enables direct conversations with Gemini for answering questions and general discussions - **File Analysis** — Analyzes various file types including images, PDFs, and text documents using Gemini's multimodal capabilities - **Flexible Configuration** — Supports different installation methods including npx and local development setups - **Model Selection** — Allows specifying different Gemini models (default: gemini-2.5-pro) for each tool ## Philosophy The project follows a minimalist approach, providing a clean wrapper that exposes Gemini CLI's core functionality through the standardized Model Context Protocol without unnecessary abstraction layers.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.