MCPgee
MCPgee
MCPgeeMCPgee

Gemini Skill

v1.0.0•Browser Automation•stable

gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶

automationbrowser-automationdrawinggeminimcp
Share:
813
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Gemini Skill?

Gemini Skill is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to gemini drawing mcp & skill through browser, can be used in openclaw or any agent that supports mcp. gemini画图 mcp和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶

gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶

This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • gemini drawing MCP & skill through browser, can be used in o

Use Cases

Gemini drawing automation through browser
Multi-agent compatibility (OpenClaw, etc.)
WJZ-P

Maintainer

LicenseMIT
Languagejavascript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx gemini-skill

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Gemini Skill

Gemini Skill is an MCP server that controls the Google Gemini web interface through the Chrome DevTools Protocol (CDP), letting AI assistants generate images, hold conversations, upload files, and extract responses from Gemini without an official API key. It exposes a rich set of MCP tools covering session management, image generation, model switching, and text retrieval. It is especially useful for OpenClaw users and any MCP-compatible agent that needs access to Gemini's image generation capabilities via browser automation.

Prerequisites

  • Node.js 18 or later installed
  • Google Chrome, Edge, or Chromium browser installed
  • A Google account with access to gemini.google.com
  • An MCP client such as Claude Desktop or OpenClaw agent
1

Clone the repository

Download the project source code to your local machine.

git clone https://github.com/WJZ-P/gemini-skill.git
cd gemini-skill
2

Install Node dependencies

Install all required npm packages listed in package.json.

npm install
3

Configure environment variables

Create a .env file or export the following variables. BROWSER_PATH defaults to auto-detection. OUTPUT_DIR controls where generated images are saved.

BROWSER_PATH=/path/to/chrome   # optional, auto-detected if omitted
BROWSER_DEBUG_PORT=40821
BROWSER_HEADLESS=false
OUTPUT_DIR=./gemini-image
4

Start the MCP server

Launch the server in MCP mode so it can receive tool calls from your client.

npm run mcp
5

Add to your MCP client config

Configure your MCP client to spawn the server using the node command from the project directory.

{
  "mcpServers": {
    "gemini-skill": {
      "command": "node",
      "args": ["/path/to/gemini-skill/dist/mcp.js"],
      "env": {
        "BROWSER_HEADLESS": "false",
        "OUTPUT_DIR": "./gemini-image"
      }
    }
  }
}

Gemini Skill Examples

Client configuration

Claude Desktop config pointing at the local gemini-skill MCP server.

{
  "mcpServers": {
    "gemini-skill": {
      "command": "node",
      "args": ["/path/to/gemini-skill/dist/mcp.js"],
      "env": {
        "BROWSER_HEADLESS": "false",
        "OUTPUT_DIR": "./gemini-images"
      }
    }
  }
}

Prompts to try

Example tool invocations once the server is connected to an MCP client.

- "Use gemini_generate_image to create a watercolor painting of a mountain lake at sunset"
- "Start a new Gemini chat with gemini_new_chat and ask it to explain quantum entanglement"
- "Upload my diagram.png to Gemini and ask for feedback"
- "Get the latest text response from the current Gemini session"

Troubleshooting Gemini Skill

Browser not found or fails to launch

Set BROWSER_PATH explicitly to the full path of your Chrome/Chromium executable, e.g. /usr/bin/google-chrome.

CDP connection refused on port 40821

Make sure no other process is using that port, or change BROWSER_DEBUG_PORT to a free port and restart the server.

Image generation times out

Gemini's web UI can be slow; increase DAEMON_TTL_MS to a higher value such as 3600000 (1 hour) to prevent the browser from being killed mid-generation.

Frequently Asked Questions about Gemini Skill

What is Gemini Skill?

Gemini Skill is a Model Context Protocol (MCP) server that gemini drawing mcp & skill through browser, can be used in openclaw or any agent that supports mcp. gemini画图 mcp和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶ It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Gemini Skill?

Follow the installation instructions on the Gemini Skill GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Gemini Skill?

Gemini Skill works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Gemini Skill free to use?

Yes, Gemini Skill is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Gemini Skill Alternatives — Similar Browser Automation Servers

Looking for alternatives to Gemini Skill? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.

Chrome DevTools MCP

★ 40.6k

AI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo

UI TARS Desktop

★ 34.9k

📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.

Playwright

★ 32.8k

A production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa

Page Agent

★ 18.0k

JavaScript in-page GUI agent. Control web interfaces with natural language.

Chrome

★ 11.7k

An extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,

LAMDA

★ 7.8k

The most powerful Android RPA agent framework, next generation mobile automation.

Browse More Browser Automation MCP Servers

Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Browser AutomationBrowse All Servers

Quick Config Preview

{ "mcpServers": { "gemini-skill": { "command": "npx", "args": ["-y", "gemini-skill"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Gemini Skill?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides