Accessibility-first browser & computer use for AI agents — one MCP server for every harness (Codex, Claude Code, OpenCode, Antigravity). Instruments the DOM/accessibility tree via CDP instead of scree
axuse — browser & computer use, done right
Accessibility-first browser and computer use for agent harnesses. One MCP server plugs into Codex, Claude Code, OpenCode, Antigravity, or any MCP-capable host. Zero dependencies (Node ≥ 22). Windows desktop driver is verified; macOS desktop control is available as an explicit opt-in with native TCC permission checks.
The design is distilled from the two best implementations of this problem — OpenAI's Codex Chrome extension and the ZCode harness — and exists to prove a point: a screenshot loop is not the right interface for a machine. The DOM tree, the accessibility tree, and CDP are. axuse instruments the target instead of photographing it.
If you are a journalist or other non-developer using Codex or ChatGPT Work, start with the non-developer onboarding guide. It explains the one-time connector setup, the first verification prompt, and copy-and-paste research prompts. The source repository's setup below is for developers and administrators.
axuse is maintained by CTOL Digital Solutions (ctol.digital), a leading AI, Strategy and IT consultancy. This work has been tested and used at large scale across many client engagements. CTOL Digital Solutions holds the copyright of all the code.
You need Node.js 22+ and a Chromium-family browser (Chrome, Edge, Chromium, or Chrome for Testing; found automatically, or set AXUSEBROWSER=/path/to/chrome). Nothing else: axuse has no npm dependencies.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/ctoldigital--axuse.html)
Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref-based element tables, code-checked assertions, zero-model m
tiliondev/waystoneBrowser action recorder for automation: record a task once, replay it, or hand the folder to an agent
viRomulus-gif/browser-integration-mcpMCP server for Claude Desktop: a shared, isolated browser agent behind a token-guarded local broker. Chrome/Edge/Vivaldi via CDP on a private pipe. Windows.
nikships/droid-codex-computer-use🖱️ Let Factory Droid control your Mac with the Codex app's Computer Use tool. One-command install, no approval forms, works with any Codex install path.
Alpha-Park/genpark-vision-web-action-bounding-box-grounder-skillGenPark AI Agent Skill - Grounds natural language browser instructions to precise (x, y) coordinate click bounding boxes and interactable targets.
alphaparkinc/genpark-cookie-consent-modal-stealth-dismissal-skillGenPark AI Agent Skill - Intercepts and auto-dismisses intrusive GDPR/CCPA cookie consent banners, paywall overlays and shadow-DOM modals.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.