Gemini Mcp
@RLabs-Inc
Gemini Mcp について
MCP Server that enables Claude code to interact with Gemini
基本情報
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.
「AI とエージェント」の他のコンテンツ
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
Model Context Protocol for Unreal Engine
chongdashuEnable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
MCP Claude Code
SDGLBLMCP implementation of Claude Code capabilities and more
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
コメント