skills.rest
george11642
george11642COMMUNITY
Explore all skills by this author →
GitHub

mcp-gemini

Orchestrate Gemini MCP tools for multimodal analysis, generation, search, and code execution.

2|Updated Jan 30, 2026
Search Tags:#multimodal#mcp#gemini#web-search#code-execution#video-analysis#image-analysis
One-click install
npx skills add https://github.com/george11642/george-plugins --skill mcp-gemini
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mcp-gemini
Source: https://github.com/george11642/george-plugins/tree/main/plugins/george-setup/skills/mcp-gemini
Command: npx skills add https://github.com/george11642/george-plugins --skill mcp-gemini

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gemini MCP unifies access to Gemini's multimodal capabilities, enabling a single framework to orchestrate chat, image analysis, image generation, grounded web search with citations, sandboxed code execution, text-to-speech, and video analysis.

Core Features & Use Cases

  • Multimodal toolset for reasoning, generation, and analysis across images, text, and video using Gemini MCP.
  • Grounded web search with citation support to fetch up-to-date information and references.
  • Sandboxed code execution and TTS for end-to-end AI-assisted workflows (including video and image tasks).

Quick Start

Ask Gemini to analyze an image, generate content, or search the web with grounded citations to start.

Frequently Asked Questions about mcp-gemini

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multimodal video and image analysis using Gemini MCP?▼

Grounded web search with citations fetches up-to-date information and references. It operates within the Gemini MCP framework to ensure retrieved web data is accurately cited and integrated into your AI-assisted generation workflow.

Can I execute sandboxed code within a Gemini MCP multimodal workflow?▼

Yes, sandboxed code execution is supported directly within the Gemini MCP framework. This allows you to run code safely end-to-end alongside text-to-speech, image generation, and video analysis tasks without leaving your AI workflow.

What Gemini model do I need to access multimodal MCP tools for AI workflows?▼

Accessing multimodal MCP tools for AI workflows requires the gemini-3.1-flash-lite-preview model. You also need access to Gemini MCP via ToolSearch to properly orchestrate analysis, generation, and search capabilities.

Does Gemini MCP support text-to-speech and image generation in the same framework?▼

Yes, Gemini MCP unifies text-to-speech and image generation within a single framework. It orchestrates these capabilities alongside grounded web search and video analysis to provide comprehensive end-to-end AI-assisted workflows.

Related Skills

Explore More Software Engineering Skills→
hwj123hwjhwj123hwj
4

vertex-video-reader

Analyze video content with Google Cloud Vertex AI's Gemini-3.1-Flash-lite-preview model.

Community
Intermediate
Cao-RCao-R

Podcast Generate

Generate podcast scripts and audio from text or web search results.

Community
Advanced
yukieijiyukieiji

deploy-to-vercel

Automates app deployment to Vercel via CLI or push with optional sandboxing support.

Community
Advanced
111pointer111111pointer111
3

minimax_model_skill

Generate audio, music, images, and video through MiniMax MCP with REST fallback.

Community
Advanced