a11ydriver-mcp v1.1.0

Zero-UI Chrome Extension & MCP Server Bridge for Autonomous AI Agents

Engineered with ❤️ by Eliyanto Sarage • [email protected]

⚡ 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 with refId tracking, saving up to 80% LLM tokens.
• 🧰 26 Full CDP MCP Tools: Complete browser control including Tab Group sessions, drag-and-drop, full-page screenshots, PDF export, JS dialog handling, file uploads, device emulation, console logs, 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.
• 🔌 Dual Stdio + SSE Transport & Multi-Port Fallback: Native Stdio JSON-RPC, WebSocket Server, and SSE stream (/sse) with runtime metadata auto-discovery (~/.a11ydriver/runtime.json).

🚀 Quick Setup & Management CLI

1. Global Installation

npm install -g a11ydriver-mcp

2. Targeted AI Client Configuration

npx a11ydriver-mcp install opencode       # OpenCode / OpenCode-Lean
npx a11ydriver-mcp install claude-code    # Claude Code CLI (~/.claude.json)
npx a11ydriver-mcp install claude-desktop # Claude Desktop
npx a11ydriver-mcp install cursor         # Cursor IDE
npx a11ydriver-mcp install windsurf       # Windsurf / Windsurf Next
npx a11ydriver-mcp install trae           # Trae IDE / Trae Agent
npx a11ydriver-mcp install roo-code       # Roo Code / Cline Extension
npx a11ydriver-mcp install continue       # Continue.dev Extension
npx a11ydriver-mcp install zed            # Zed Editor

3. Local Workspace Setup

npx a11ydriver-mcp init-project

4. Audit & Diagnostics

npx a11ydriver-mcp list    # List all 25+ supported AI targets & docs
npx a11ydriver-mcp scan    # Audit installed AI tools & status
npx a11ydriver-mcp doctor  # Diagnostic health check & WebSocket probe
npx a11ydriver-mcp launch  # Auto-launch Chrome with extension preloaded

🛠️ Complete MCP Tool Protocol (26 Tools)

| Tool Category | MCP Tool Name | Description | | :--- | :--- | :--- | | Tab & Group | browser_launch | Auto-launch Google Chrome with A11yDriver extension preloaded | | | browser_list_tabs | List all open Chrome tabs with IDs & titles | | | browser_new_tab | Open a new tab (optional url, groupId) | | | browser_create_agent_group | Create an isolated tab group for AI agent session | | | browser_cleanup_agent_group | Close all tabs inside an agent tab group after task finishes | | | browser_switch_tab | Switch active focused tab by tabId | | | browser_close_tab | Close specified tab by tabId | | Navigation | browser_navigate | Navigate active tab to target url | | | browser_go_back | Go back in browser history | | | browser_go_forward | Go forward in browser history | | | browser_reload | Reload current page | | Interactions | browser_click | Click element by coordinates (x, y) or element refId | | | browser_hover | Hover cursor over element or (x, y) coordinates | | | browser_drag_and_drop | Perform drag & drop from (fromX, fromY) to (toX, toY) | | | browser_type | Type text into element refId or active input | | | browser_press_key | Press special keys (Enter, Tab, Escape, Backspace, ArrowDown, ArrowUp) | | | browser_scroll | Scroll page vertically (deltaY) or horizontally (deltaX) | | Advanced CDP | browser_handle_dialog | Accept or dismiss JS alert(), confirm(), prompt() popups | | | browser_upload_file | Upload local file to file input refId | | | browser_emulate_device | Emulate mobile screen viewport and device metrics | | | browser_get_console_logs | Retrieve JS console error/warning history | | DOM & Output | browser_get_a11y_tree | Get semantic Accessibility Tree snapshot with refId | | | browser_evaluate_script | Execute custom JS snippet on web context via CDP Runtime | | | browser_screenshot | Capture tab screenshot (supports fullPage: true) | | | browser_print_to_pdf | Print web page to PDF base64 document | | | browser_get_cookies | Get session cookies for active domain |

Developed by Eliyanto Sarage ([email protected])

Released under the MIT License.