MCP.so
ログイン

Gemini Mcp

@RLabs-Inc

Gemini Mcp について

MCP Server that enables Claude code to interact with Gemini

基本情報

カテゴリ

AI とエージェント

ライセンス

MIT license

ランタイム

node

トランスポート

stdio

公開者

RLabs-Inc

投稿者

Rodrigo Luglio

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "gemini-mcp": {
      "command": "bun",
      "args": [
        "run",
        "build"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Gemini Mcp?

Gemini Mcp is a Model Context Protocol (MCP) server that integrates Google's Gemini 3 models with Claude Code, enabling direct access to Gemini's capabilities—such as image/video generation, deep research, code execution, and web search—from within a Claude Code session. It is designed for developers who want to combine Gemini's creative and analytical tools with Claude's coding and reasoning workflows, and it also ships with a standalone CLI.

How to use Gemini Mcp?

Install via npm (@rlabs-inc/gemini-mcp) and add it to Claude Code with claude mcp add gemini -s user -- env GEMINI_API_KEY=YOUR_KEY npx -y @rlabs-inc/gemini-mcp. Alternatively, install globally (npm install -g @rlabs-inc/gemini-mcp) and use the gcli CLI. Set your API key once with gcli config set api-key YOUR_KEY and then invoke any tool (e.g., gcli image, gcli search) directly from the terminal.

Key features of Gemini Mcp

  • Deep research agent with web search and citations
  • 4K image generation with 10 aspect ratios
  • Multi-turn image editing through conversation
  • Video generation using Veo 2.0 (async polling)
  • Code execution with Python libraries (numpy, pandas, matplotlib)
  • Real-time web search with inline citations

Use cases of Gemini Mcp

  • Generate UI mockups and React components during a Claude Code development session
  • Analyze YouTube videos by URL with timestamp clipping and summarization
  • Extract tables and data from PDFs, DOCX, and spreadsheets
  • Brainstorm solutions collaboratively between Claude and Gemini
  • Summarize long documents at configurable detail levels (brief, moderate, detailed)

FAQ from Gemini Mcp

What API key is required?

A Google Gemini API key from Google AI Studio — it is free and takes seconds to obtain.

How do I handle rate limits (429 errors)?

Set GEMINI_MODEL=gemini-3-flash-preview to use the Flash model for initialization (higher rate limits), or upgrade to a paid Google AI plan.

Where are generated files saved?

Files are saved to the directory specified by GEMINI_OUTPUT_DIR (defaults to ./gemini-output in the working directory).

What models does Gemini Mcp use?

It uses Gemini 3 Pro/Flash for queries, Nano Banana Pro for images, Veo 2.0 for videos, and supports configurable model overrides via environment variables.

How can I troubleshoot connection issues?

Verify your API key at Google AI Studio, check the server status with claude mcp list, and enable verbose logging by setting VERBOSE=true in the environment.

コメント

「AI とエージェント」の他のコンテンツ