Gemini Mcp

MCP Server Gemini

A Model Context Protocol (MCP) server for integrating Google's Gemini 3 models with Claude Code, enabling powerful collaboration between both AI systems. Now with a beautiful CLI!

[npm version] [MCP Registry]

MCP Registry Support: Now discoverable in the official MCP ecosystem!

Features

Quick Installation

MCP Server for Claude Code

# Using npm (Recommended)claude mcp add gemini -s user -- env GEMINI_API_KEY=YOUR_KEY npx -y @rlabs-inc/gemini-mcp
# Using bunclaude mcp add gemini -s user -- env GEMINI_API_KEY=YOUR_KEY bunx @rlabs-inc/gemini-mcp

CLI (Global Install)

# Install globallynpm install -g @rlabs-inc/gemini-mcp
# Set your API key once (stored securely)gcli config set api-key YOUR_KEY
# Now use any command!gcli search "latest news"glci image "sunset over mountains" --ratio 16:9

Get your API key: Visit Google AI Studio - it's free and takes seconds!

Installation Options

# With verbose loggingclaude mcp add gemini -s user -- env GEMINI_API_KEY=YOUR_KEY VERBOSE=true bunx -y @rlabs-inc/gemini-mcp
# With custom output directory for generated images/videosclaude mcp add gemini -s user -- env GEMINI_API_KEY=YOUR_KEY GEMINI_OUTPUT_DIR=/path/to/output bunx -y @rlabs-inc/gemini-mcp

Available Tools

gemini-query

Direct queries to Gemini with thinking level control:

prompt: "Explain quantum entanglement"model: "pro" or "flash"thinkingLevel: "low" | "medium" | "high" (optional)

• low: Fast responses, minimal reasoning
• medium: Balanced (Flash only)
• high: Deep reasoning for complex tasks (default)

gemini-generate-image

Generate images with Nano Banana Pro (Claude can SEE them!):

prompt: "a futuristic city at sunset"style: "cyberpunk" (optional)aspectRatio: "16:9" (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9)imageSize: "2K" (1K, 2K, 4K)useGoogleSearch: false (ground in real-world info)thinkingLevel: "high" (optional - minimal, low, medium, high)personGeneration: "ALLOW_ALL" (optional - ALLOW_ALL, ALLOW_ADULT, ALLOW_NONE)seed: 42 (optional - for reproducible results)

gemini-start-image-edit

Start a multi-turn image editing session:

prompt: "a cozy cabin in the mountains"aspectRatio: "16:9"imageSize: "2K"useGoogleSearch: falsethinkingLevel: "high" (optional - minimal, low, medium, high)personGeneration: "ALLOW_ALL" (optional - ALLOW_ALL, ALLOW_ADULT, ALLOW_NONE)seed: 42 (optional - for reproducible results)

Returns a session ID for iterative editing.

gemini-continue-image-edit

Continue refining an image:

sessionId: "edit-123456789"prompt: "add snow on the roof and make it nighttime"

gemini-end-image-edit

Close an editing session:

sessionId: "edit-123456789"

gemini-list-image-sessions

List all active editing sessions.

gemini-generate-video

Generate videos using Veo:

prompt: "a cat playing piano"aspectRatio: "16:9" (optional)negativePrompt: "blurry, text" (optional)

Video generation is async (takes 1-5 minutes). Use gemini-check-video to poll.

gemini-check-video

Check video generation status and download when complete:

operationId: "operations/xxx-xxx-xxx"

gemini-analyze-code

Analyze code for issues:

code: "function foo() { ... }"language: "typescript" (optional)focus: "quality" | "security" | "performance" | "bugs" | "general"

gemini-analyze-text

Analyze text content:

text: "Your text here..."type: "sentiment" | "summary" | "entities" | "key-points" | "general"

gemini-brainstorm

Collaborative brainstorming:

prompt: "How could we implement real-time collaboration?"claudeThoughts: "I think we should use WebSockets..."maxRounds: 3 (optional)

gemini-summarize

Summarize content:

content: "Long text to summarize..."length: "brief" | "moderate" | "detailed"format: "paragraph" | "bullet-points" | "outline"

gemini-run-code

Let Gemini write and execute Python code:

prompt: "Calculate the first 50 prime numbers and plot them"data: "optional CSV data to analyze" (optional)

Supports libraries: numpy, pandas, matplotlib, scipy, scikit-learn, tensorflow, and more. Generated charts are saved to the output directory and returned as images.

gemini-search

Real-time web search with citations:

query: "What happened in tech news this week?"returnCitations: true (default)

Returns grounded responses with inline citations and source URLs.

gemini-structured

Get JSON responses matching a schema:

prompt: "Extract the meeting details from this email..."schema: '{"type":"object","properties":{"date":{"type":"string"},"attendees":{"type":"array"}}}'useGoogleSearch: false (optional)

gemini-extract

Convenience tool for common extraction patterns:

text: "Your text to analyze..."extractType: "entities" | "facts" | "summary" | "keywords" | "sentiment" | "custom"customFields: "name, date, amount" (for custom extraction)

gemini-youtube

Analyze YouTube videos directly:

url: "https://www.youtube.com/watch?v=..."question: "What happens at 2:30?"startTime: "1m30s" (optional, for clipping)endTime: "5m00s" (optional, for clipping)

gemini-youtube-summary

Quick video summarization:

url: "https://www.youtube.com/watch?v=..."style: "brief" | "detailed" | "bullet-points" | "chapters"

gemini-analyze-document

Analyze PDFs and documents:

filePath: "/path/to/document.pdf"question: "Summarize the key findings"mediaResolution: "low" | "medium" | "high"

gemini-summarize-pdf

Quick PDF summarization:

filePath: "/path/to/document.pdf"style: "brief" | "detailed" | "outline" | "key-points"

gemini-extract-tables

Extract tables from documents:

filePath: "/path/to/document.pdf"outputFormat: "markdown" | "csv" | "json"

Workflow: Claude + Gemini

The killer combination for development:

Example workflow:

1. Ask Claude to design the backend API
2. Use gemini-generate-image for UI mockups
3. Ask Gemini to generate React components via gemini-query
4. Use multi-turn editing to refine visuals
5. Let Claude wire everything together

Environment Variables

Tool Configuration

By default, all 37 tools are loaded. To reduce context usage, configure which tools to load:

Available Presets

Using Presets

# Minimal - query and brainstormGEMINI_TOOL_PRESET=minimal
# Text processingGEMINI_TOOL_PRESET=text  # query, brainstorm, analyze, summarize, structured
# Image workflowsGEMINI_TOOL_PRESET=image  # query, image-gen, image-edit, image-analyze
# Research workflowsGEMINI_TOOL_PRESET=research  # query, search, deep-research, url-context, document

Using Explicit Tool Lists

# Only specific toolsGEMINI_ENABLED_TOOLS=query,search,image-gen

Combining Preset + Explicit

# Start with preset, add extrasGEMINI_TOOL_PRESET=minimalGEMINI_ENABLED_TOOLS=search,image-gen  # Adds to minimal preset

Available Tool Groups

Manual Installation

Global Install

# Using npmnpm install -g @rlabs-inc/gemini-mcp
# Using bunbun install -g @rlabs-inc/gemini-mcp

Claude Code Configuration

{  "gemini": {    "command": "npx",    "args": ["-y", "@rlabs-inc/gemini-mcp"],    "env": {      "GEMINI_API_KEY": "your-api-key",      "GEMINI_OUTPUT_DIR": "/path/to/save/files"    }  }}

If you must use a proxy to establish a connection to gemini, replace xxxx with your actual proxy port:

{  "gemini": {    "command": "npx",    "args": ["-y", "@rlabs-inc/gemini-mcp"],    "env": {      "GEMINI_API_KEY": "your-api-key",      "GEMINI_OUTPUT_DIR": "/path/to/save/files",      "HTTP_PROXY": "http://127.0.0.1:xxxx",      "HTTPS_PROXY": "http://127.0.0.1:xxxx"    }  }}

Troubleshooting

Rate Limits (429 Errors)

If you're hitting rate limits on the free tier:

• Set GEMINI_MODEL=gemini-3-flash-preview to use Flash for init (higher limits)
• Or upgrade to a paid plan

Connection Issues

1. Verify your API key at Google AI Studio
2. Check server status: claude mcp list
3. Try with verbose logging: VERBOSE=true

Image/Video Issues

• Ensure your API key has access to image/video generation
• Check output directory permissions
• Files save to GEMINI_OUTPUT_DIR (default: ./gemini-output)
• For 4K images, generation takes longer

Previous Versions

0.7.2

Beautiful CLI with Themes! Use Gemini directly from your terminal:

# Install globallynpm install -g @rlabs-inc/gemini-mcp
# Set your API key oncegcli config set api-key YOUR_KEY
# Generate images, videos, search, research, and more!gcli image "a cat astronaut" --size 4Kgcli search "latest AI news"gcli research "quantum computing applications" --waitgcli speak "Hello world" --voice Puck

5 Beautiful Themes: terminal, neon, ocean, forest, minimal

CLI Commands:

• gcli query - Direct Gemini queries with thinking levels
• gcli search - Real-time web search with citations
• gcli research - Deep research agent
• gcli image - Generate images (up to 4K)
• gcli video - Generate videos with Veo
• gcli speak - Text-to-speech with 30 voices
• gcli tokens - Count tokens and estimate costs
• gcli config - Manage settings

v0.6.x: Deep Research, Token Counting, TTS, URL analysis, Context Caching v0.5.x: 30+ tools, YouTube analysis, Document analysis v0.4.x: Code execution, Google Search v0.3.x: Thinking levels, Structured output, 4K images v0.2.x: Image/Video generation with Veo

Development

git clone https://github.com/rlabs-inc/gemini-mcp.gitcd gemini-mcpbun installbun run buildbun run dev -- --verbose

Scripts

License

MIT License

Made with Claude + Gemini working together