Kilo Computer Use — Chrome Extension Bridge

MCP server that connects AI agents to your real Chrome browser via a WebSocket extension bridge. No debug mode, no profile isolation, no killed sessions.

Quick Start

1. Install

git clone https://github.com/YOUR_USERNAME/kilo-computer-use.git
cd kilo-computer-use
npm install
npm run build

2. Load Extension in Chrome

1. Open chrome://extensions/
2. Enable Developer mode
3. Click Load unpacked
4. Select the extension/ folder from this project
5. Click the Kilo Browser Bridge icon → Connect to MCP

3. Use in Kilo

The MCP server auto-starts on port 9444. All 40+ browser tools are available.

Architecture

MCP Server (Node.js, port 9444)
    ↕ WebSocket
Chrome Extension (MV3, service worker)
    ↕ Chrome APIs
Your real Chrome (bookmarks, sessions, extensions)

Tools

Tab Management

• browser_list_pages — List all tabs
• browser_new_page — Open new tab
• browser_select_page — Switch tabs
• browser_close_page — Close tab
• browser_pin_tab — Pin/unpin tab
• browser_duplicate_tab — Clone tab
• browser_mute_tab — Mute/unmute
• browser_move_tab — Reorder tabs
• browser_tab_info — Tab metadata

Navigation

• browser_navigate — Go to URL
• browser_back / browser_forward — History
• browser_reload — Reload page
• browser_stop — Stop loading
• browser_open_homepage — New tab page

Interaction

• browser_click / browser_click_at — Click elements
• browser_double_click / browser_right_click — Advanced clicks
• browser_type / browser_type_at — Type text
• browser_fill — Set input value
• browser_clear_field — Clear input
• browser_submit — Submit form
• browser_focus — Focus element
• browser_check — Toggle checkbox
• browser_select — Dropdown select
• browser_hover — Hover element
• browser_scroll / browser_scroll_to / browser_scroll_element — Scroll
• browser_select_text — Select text
• browser_drag_drop — Drag and drop
• browser_key — Press keyboard key

Page Inspection

• browser_screenshot — Capture visible tab
• browser_content — Get page text/HTML
• browser_page_info — Page metadata
• browser_evaluate — Run JavaScript
• browser_execute_script — Execute JS code
• browser_inject_css — Inject custom CSS
• browser_element_info — Element details
• browser_get_elements — Query elements
• browser_get_attribute / browser_set_attribute — Read/write attributes
• browser_get_cookies / browser_set_cookie — Cookie management
• browser_find_text — Search page text
• browser_get_links / browser_get_images / browser_get_forms / browser_get_meta — Extract structure
• browser_wait / browser_wait_for_text — Wait for elements

Clipboard

• browser_copy_text / browser_paste_text — Clipboard access

Media

• browser_play_media / browser_pause_media / browser_seek_media / browser_media_info — Video/audio control

Window

• browser_get_viewport / browser_fullscreen — Viewport management

Bookmarks & History

• browser_get_bookmarks / browser_add_bookmark / browser_search_bookmarks
• browser_get_history / browser_add_history / browser_delete_history / browser_clear_history
• browser_download — Trigger file download
• browser_notify — Chrome notification

Desktop (OS-level)

• desktop_screenshot / desktop_click / desktop_type / desktop_key / desktop_scroll / desktop_move / desktop_drag

Tech Stack

• TypeScript + Node.js
• Chrome Extension Manifest V3
• WebSocket (ws) for bridge communication
• MCP SDK (@modelcontextprotocol/sdk)
• Chrome Extension APIs (tabs, scripting, bookmarks, history, downloads, notifications)

License

MIT