a11ydriver-mcp
Provides tools for controlling Google Chrome browser, including tab management, navigation, clicking, typing, screenshots, PDF export, and accessibility tree inspection via CDP.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@a11ydriver-mcpopen example.com and take a full page screenshot"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A11yDriver Engine
Zero-UI Chrome Extension & MCP Server Bridge for Autonomous AI Agents
Engineered with ❤️ by Eliyanto Sarage • officialelsa21@gmail.com
⚡ Key Highlights & Architecture
🛡️ Zero-UI Background Operator: Operates 100% silently in Chrome service worker without popup or sidepanel overhead.
🌳 Accessibility Tree Serializer (
a11y-engine.js): Converts complex DOM + Shadow DOM trees into compressed semantic trees withrefIdtracking, saving up to 80% LLM tokens.🧰 21 Full CDP MCP Tools: Complete browser control including Tab Group sessions, drag-and-drop, full-page screenshots, PDF export, hover triggering, and key pressing.
🔒 Sensitive Data Redaction: Automatic local masking of password fields, OTPs, and credit card credentials.
⏱️ Manifest V3 Keep-Alive: Heartbeat alarms prevent Service Worker sleep during extended AI agent sessions.
Related MCP server: Chrome MCP Server
🚀 Quick Setup
1. Install Global MCP Server
npm install -g a11ydriver-mcp2. Configure AI Agent (Claude Code / Claude Desktop / Custom Agent Host)
Add a11ydriver-mcp to your MCP configuration:
{
"mcpServers": {
"a11ydriver": {
"command": "a11ydriver-mcp"
}
}
}3. Load Extension in Chrome
Open
chrome://extensionsin Google Chrome.Turn on Developer mode.
Click Load unpacked and select the
extension/directory.
4. Enable Agent Diagnostic Protocol (System Prompt)
Copy and paste the prompt in AGENT_INSTRUCTIONS.md into your AI Agent's system instructions. This ensures the AI Agent automatically detects whether MCP & Extension are connected and diagnoses any missing setup steps.
🛠️ Complete MCP Tool Protocol (21 Tools)
Tool Category | MCP Tool Name | Description |
Tab & Group |
| List all open Chrome tabs with IDs & titles |
| Open a new tab (optional | |
| Create an isolated tab group for AI agent session | |
| Close all tabs inside an agent tab group after task finishes | |
| Switch active focused tab by | |
| Close specified tab by | |
Navigation |
| Navigate active tab to target |
| Go back in browser history | |
| Go forward in browser history | |
| Reload current page | |
Interactions |
| Click element by coordinates |
| Hover cursor over element or | |
| Perform drag & drop from | |
| Type text into element | |
| Press special keys ( | |
| Scroll page vertically ( | |
DOM & Output |
| Get semantic Accessibility Tree snapshot with |
| Execute custom JS snippet on web context via CDP Runtime | |
| Capture tab screenshot (supports | |
| Print web page to PDF base64 document | |
| Get session cookies for active domain |
Developed by Eliyanto Sarage (officialelsa21@gmail.com)
Released under the MIT License.
This server cannot be deployed
Maintenance
Related MCP Connectors
A paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,
Live browser debugging for AI assistants — DOM, console, network via MCP.
- mcpOAuthcom.screenshotink
Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.
Hyperbrowser MCP — wraps the Hyperbrowser AI-agent browsing API
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI agents to control a real Google Chrome instance using specific user profiles, cookies, and extensions. It provides 18 tools for browser navigation, element interaction, and page inspection via the Chrome DevTools Protocol.-
- AlicenseNot gradedqualityNot gradedmaintenanceAn extension-based MCP server that enables AI assistants to control your existing Chrome browser, leveraging your active login states and settings for automation. It provides over 20 tools for tasks like semantic tab search, screen capture, network monitoring, and direct element interaction.-
- -licenseNot gradedqualityNot gradedmaintenanceMCP server that connects AI agents to a real Chrome browser via a WebSocket extension bridge, enabling over 40 browser control tools without debug mode or profile isolation.-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to control Chrome browser actions like navigation, clicking, form filling, screenshots, and console/network logging via an MCP server and Chrome extension.545 npmMIT