Best for
- Developers or AI agents needing to automate Gemini web operations.
- Users wanting to leverage Gemini image generation within the MCP ecosystem.
- Technical users comfortable with configuration and browser automation.
G
Gemini Skill
Community
Control Gemini web via CDP for AI image generation, chat, image extraction, and more.
GitHub source repository ↗
41FMRS · D
This project offers comprehensive control over Gemini web via browser automation, feature-rich but requiring environment setup and login state, suitable for technical users.
This is an MCP server and skill that controls the Gemini web interface via browser automation (CDP), enabling AI image generation, multi-turn chat, image upload/extraction, session management, and more. It uses a standalone daemon to manage the browser lifecycle, supports automatic watermark removal, reference-image generation, full-size HD downloads, and includes stealth anti-bot plugins. Works with OpenClaw or any MCP-capable client, and also provides an optional Atlas Cloud Provider for OpenAI-compatible API access.
Tools
gemini_generate_image
Full image generation flow with reference image and HD download, takes 60-120s.
gemini_new_chat
Start a new blank conversation.
gemini_temp_chat
Enter temporary chat mode.
gemini_navigate_to
Navigate to a specific Gemini URL (e.g., historical session).
gemini_switch_model
Switch model (pro/flash/flash-lite).
gemini_send_message
Send text and wait for reply, takes 10-60s.
gemini_upload_images
Upload images to the input box.
gemini_get_images
Get metadata of all images in the session.
gemini_extract_image
Extract image base64 and save locally.
gemini_download_full_size_image
Download full-size HD image.
gemini_share_latest_image
Create a public share link for the image.
gemini_get_all_text_responses
Get all text responses.
gemini_get_latest_text_response
Get the latest text response.
gemini_check_login
Check Google login status.
gemini_probe
Probe page element status.
gemini_reload_page
Reload the page.
gemini_browser_info
Get browser connection info.
Setup
Prerequisites: Node.js ≥ 18, Chrome/Edge/Chromium installed, and logged into Google account.
- Clone: git clone https://github.com/WJZ-P/gemini-skill.git
- cd gemini-skill
- npm install
- Configure environment variables (optional, e.g., BROWSER_PATH, BROWSER_DEBUG_PORT)
- Add server to MCP client config, e.g., {"mcpServers":{"gemini":{"command":"node","args":["<absolute path>/src/mcp-server.js"]}}}
claude_desktop_config.json
{
"mcpServers": {
"gemini": {
"command": "node",
"args": [
"<项目绝对路径>/src/mcp-server.js"
]
}
}
}
Fit and risk
Not for
- Non-technical users who need simple setup.
- Scenarios requiring official API support or large-scale production.
- Users needing high stability and intolerant of browser automation fragility.
Required permissions
- Requires read/write access to browser user data directory (including login state).
- Requires local file system access to save generated images.
- Requires network access to connect to Gemini web and Atlas Cloud API (if used).
Risks and side effects
- Depends on browser automation; may break if Gemini UI changes.
- Requires Google account login; account security risk.
- Browser automation may violate website terms of service.
- Image generation can be slow and may time out.
Troubleshooting
- Common issues:
- - Login failure: Ensure browser is non-headless, manually login and save user data directory.
- - Port conflict: Ensure CDP port (default 40821) is free or change BROWSER_DEBUG_PORT.
- - Timeouts: Increase MCP client timeoutMs to 180000ms or more.
- - Browser launch failure: Check BROWSER_PATH or install a supported browser.
- - Model switch failure: Confirm using new model names (pro/flash/flash-lite).
Use cases
AI image generation: create images from natural language prompts.
Text chat: interact with Gemini in multi-turn conversations.
Image processing: upload reference images for image-to-image generation or extract images from conversations.
Automation workflows: integrate Gemini capabilities into OpenClaw or other MCP clients.
Supported clients
Claude DesktopFull support
CodeBuddyFull support
OpenClawFull support