AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions kept in code. Accessibi
AX-first macOS computer use for AI agents: an MCP server and a CLI. Agents read the accessibility tree instead of guessing coordinates from screenshots. Input is posted to the target app in the background, so your cursor never moves, and every action is verified.
- One command per client. Works with Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, opencode, pi and DeepSeek Harness. It is a stdio MCP server with no runtime dependencies beyond pyobjc and Pillow. - Accessibility first. Each element comes back with a stable ref, its role, its label and exact screen geometry. Re-observing returns only the diff. Electron and Chromium apps get their full tree turned on automatically. - Background input. Clicks, keys, scrolls, drags and Unicode typing are posted to the target process, so the user can keep working. CJK, emoji and accents arrive intact, and the clipboard is left alone. - Verified, never optimistic. Every result separates actionsent from verified. Failures say whether it is safe to retry, whether to reobserve, or whether to never retry. - Safe by default. There is a built-in deny list for password managers and system auth. The kit refuses to type into a password field that holds Secure Event Input, redacts secure fields, and blocks lock, log-out and force-quit chords. It also offers a dry-run mode, a size-only audit log and app allow/deny lists. - Vision only when needed. Set-of-mark screenshots draw numbered marks linked to refs, and on-device Apple Vision OCR returns screen coordinates. Both are fallbacks for canvas, game and custom-drawn UI.
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/Sur-Cai--macos-computer-use-kit.html)
Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th
surendranb/writing-skillsProcedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer docs) + character voices. Agent Plugins 1.0.0, works in openc
dontpayfull/AInotateAnnotated screenshots for AI agents: Skitch-style arrows, numbered steps, boxes, labels, solid redaction
dongnguyenvie/bashcut-agent-kitBashCut's agent kit: editing skills (footage survey, beat cuts, audio mix, captions, colour, voiceover…) and the BashCut MCP server for Claude Code and Codex.
ateymoori/oh-my-androidAndroid emulator & ADB GUI for Mac: dark mode, font size, RTL, TalkBack, network, GPS, Layout Inspector in dp. Built-in MCP server lets Claude Code, Codex and Cursor drive the emulator.
ghorbelhamdi/buddy-androidA floating chat bubble that lets Claude Code, Codex or OpenCode use your Android phone. Runs inside the app on your own subscription or free models. No adb, no PC, no root.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.