How do I install the Gemini MCP skill?

Run npx skillmds@latest add neuron-one/gemini-mcp in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Gemini MCP skill do?

Delegates text tasks to Google Gemini through MCP (gemini/gemini-reply). Use for architecture disputes, design critique, second opinions. Don't use for media — use gemini-media for images/video. It is listed under AI & ML on SkillMD.

Is Gemini MCP safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Gemini MCP?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Gemini MCP free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Gemini MCP?

neuron-one (@neuron-one) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Gemini MCP by neuron-one — Agent Skill

Name: Gemini MCP
Author: neuron-one

File contents

Gemini MCP Integration

Two Gemini Servers

`gemini` (Text — Delegator Bridge)

Tools: mcp__gemini__gemini, mcp__gemini__gemini-reply
Use for: architecture disputes, code review, design critique, text consultations
Powered by: Gemini CLI → Gemini 2.5 Flash/Pro
Supports: multi-turn (threadId), developer-instructions, sandbox modes

`gemini-media` (Media — @fre4x/gemini)

Tools: mcp__gemini-media__analyze_media, mcp__gemini-media__generate_image, mcp__gemini-media__generate_video
Use for: image analysis, image generation (Imagen), video generation (Veo)
Powered by: Gemini API directly

When to Use Gemini (Text)

As independent expert in /dispute (full text architecture/design reviews)
Design and visual critique (describe, don't just send image)
Second opinion on Claude's decisions
Tasks where Google ecosystem knowledge helps

When to Use Gemini-Media

Analyze screenshots, diagrams, photos
Generate images (Imagen)
Generate videos (Veo)

Rules

Include full context (Gemini doesn't see our conversation)
Specify output format expected
Compare with Claude's own analysis
Note: data sent to Google servers

Frequently asked questions

Gemini MCP