kilo-computer-use
MCP 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.
README
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
- Open
chrome://extensions/ - Enable Developer mode
- Click Load unpacked
- Select the
extension/folder from this project - 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 tabsbrowser_new_page— Open new tabbrowser_select_page— Switch tabsbrowser_close_page— Close tabbrowser_pin_tab— Pin/unpin tabbrowser_duplicate_tab— Clone tabbrowser_mute_tab— Mute/unmutebrowser_move_tab— Reorder tabsbrowser_tab_info— Tab metadata
Navigation
browser_navigate— Go to URLbrowser_back/browser_forward— Historybrowser_reload— Reload pagebrowser_stop— Stop loadingbrowser_open_homepage— New tab page
Interaction
browser_click/browser_click_at— Click elementsbrowser_double_click/browser_right_click— Advanced clicksbrowser_type/browser_type_at— Type textbrowser_fill— Set input valuebrowser_clear_field— Clear inputbrowser_submit— Submit formbrowser_focus— Focus elementbrowser_check— Toggle checkboxbrowser_select— Dropdown selectbrowser_hover— Hover elementbrowser_scroll/browser_scroll_to/browser_scroll_element— Scrollbrowser_select_text— Select textbrowser_drag_drop— Drag and dropbrowser_key— Press keyboard key
Page Inspection
browser_screenshot— Capture visible tabbrowser_content— Get page text/HTMLbrowser_page_info— Page metadatabrowser_evaluate— Run JavaScriptbrowser_execute_script— Execute JS codebrowser_inject_css— Inject custom CSSbrowser_element_info— Element detailsbrowser_get_elements— Query elementsbrowser_get_attribute/browser_set_attribute— Read/write attributesbrowser_get_cookies/browser_set_cookie— Cookie managementbrowser_find_text— Search page textbrowser_get_links/browser_get_images/browser_get_forms/browser_get_meta— Extract structurebrowser_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_bookmarksbrowser_get_history/browser_add_history/browser_delete_history/browser_clear_historybrowser_download— Trigger file downloadbrowser_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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.