macos-use
GUI control for macOS apps via mediar-ai's mcp-server-macos-use.
Skill by rudyalways
Chalk Labs
Need help deploying macos-use?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/rudyalways-macos-use
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
macos-use- Description
- GUI control for macOS apps via mediar-ai's mcp-server-macos-use. Click, type, scroll, key-press, open apps — driven by accessibility tree, works in non-interactive Claude Code mode. Use this for any Sutando task that needs to drive another macOS application (Safari, Zoom, Mail, Finder, etc.).
- License
- MIT
- Instructions
- 83 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- manifest.json
- build.sh · scripts/
- install-mcp.sh · scripts/
SKILL.md (first lines)
# macos-use Drive macOS applications from Claude Code via mediar-ai's [mcp-server-macos-use](https://github.com/mediar-ai/mcp-server-macos-use). A Swift MCP server that wraps the macOS Accessibility API. Unlike Claude's built-in `computer-use`, this works in non-interactive mode (which is how Sutando's proactive loop and task bridge run), does not hold a machine-wide lock, and does not require a Pro/Max subscription. ## When to use - "Open Safari and navigate to github.com" — anything requiring real GUI interaction with an app - "Click the Join button on the Zoom invite dialog" - "Type this into the Discord message box" - "Scroll the frontmost window to the bottom" - Any task that currently falls back to AppleScript + Quartz mouse events in `src/inline-tools.ts` - Screen questions where structured UI is more useful than pixels, such as "what controls are visible in this app?" Prefer this skill over: - `bash src/screen-capture.sh` — that captures screenshots; `macos-use` actually *interacts* - AppleScript `tell application` blocks — more reliable, better error handling - `cliclick` — lower-level, no accessibility context - Claude's built-in `computer-use` — that mode requires interactive sessions and holds a lock that contends with Sutando's own loop For screen-reading only, use this order: 1. `macos-use` MCP when the active app exposes useful accessibility controls or the task may require clicking/typing next. 2. `/usr/sbin/screencapture` through the `macos-tools` screen capture script when the user asks to visually describe the screen, image, layout, or anything canvas-like. 3. Host-provided "describe screen" context when available and enough for the question. 4. For logged-in websites, keep using the user's existing visible browser session through `macos-use` or screenshots. Avoid Playwright/Chromium/browser MCP when it would require another login, a fresh profile, missing cookies, or session changes. 5. Browser/Playwright/Chromium tooling only when the user explicitly asks for browser automation/debugging, or when the page can be inspected without additional login/session setup. ## Tools exposed After install, these appear as `mcp__macos-use__*` in Claude Code: | Tool | Parameters | Purpose | |------|------------|---------| | `open_application_and_traverse` | `identifier` (name/bundle ID/path) | Launch or activate an app, return its a11y tree | | `click_and_traverse` | `pid`, `x`, `y` | Click at coordinates in a target app, return updated tree | | `type_and_traverse` | `pid`, `text` | Type into the frontmost element | | `press_key_and_traverse` | `pid`, `key` | Press a named key (Return, Tab, Escape, arrows, ...) | | `scroll_and_traverse` | `pid`, `direction`, `amount` | Scroll in a direction | | `refresh_traversal` | `pid` | Re-read the a11y tree without acting | Every tool returns an accessibility-tree snapshot of the target app — structured UI elements with roles, titles, positions, and identifiers. No pixels. Model reasons over the tree, not over screenshots. ## Install Two steps, one-time: ```bash # 1. Build the Swift binary (~35s) bash skills/macos-use/scripts/build.sh # 2. Register with Claude Code's MCP config (writes ~/.claude.json) bash skills/macos-use/scripts/install-mcp.sh # 3. Grant Accessibility permission # System Settings → Privacy & Security → Accessibility # Click +, navigate to ~/.macos-use-mcp/.build/release/mcp-server-macos-use, enable. ``` Restart Claude Code after install for the MCP tools to appear. ## Gotchas - **Swift 6 build fragility**: the `swift-sdk` transitive dep has data-race errors that Swift 6.3+ strict-concurrency trips on. `build.sh` uses `-Xswiftc -swift-version -Xswiftc 5` as a workaround. When upstream fixes this, remove the flag. - **Accessibility permission**: the binary must be added to System Settings → Privacy & Security → Accessibility, or every tool call will return "not authorized". First-run error is obvious; owner must click through once. - **Apps without good a11y trees**: Canvas / Electron / games degrade badly. For those, fall back to `screen-capture.sh` + Claude vision. - **Build dep pulled from GitHub**: air-gapped Macs won't work. No prebuilt releases yet. - **Multi-node**: each node builds its own binary. Not synced via `sutando-memory.git` (binaries are machine-specific). Run `build.sh` + `install-mcp.sh` on Mac Mini and MacBook separately. ## Quick self-test After install + restart: ``` Sutando, open Safari and navigate to https://github.com/sonichi/sutando ``` You should see Claude invoke `mcp__macos-use__open_application_and_traverse` with `identifier: "Safari"`, then `type_and_traverse` into the URL bar, then `press_key_and_traverse` with `Return`. ## Related - Research + decision memo: `notes/issue-65-computer-use-research.md` - Issue: [#65 Add Claude Computer Use support](https://github.com/sonichi/sutando/issues/65) - Upstream: https://github.com/mediar-ai/mcp-server-macos-use
From rudyalways/PhonePcLiveAgentsV2, MIT.
More from rudyalways/PhonePcLiveAgentsV2
- 0.563score
claude-router
rudyalways
Choose between the local Codex CLI and Gemini CLI from Claude Code.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
claude-gemini
rudyalways
Use the local Gemini CLI from Claude Code with the user's existing Gemini authentication or API configuration.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
image-generation
rudyalways
Generate and edit images using Gemini Flash Image, and generate videos using Veo.
SkillBFreshness: B★ 2Claude Code +9 - 0.303score
doc-ingest
rudyalways
No description from the publisher yet.
SkillBFreshness: B★ 2Claude Code +9 - 0.300score
agent-room-ops
rudyalways
No description from the publisher yet.
SkillBFreshness: B★ 2Claude Code +9 - 0.300score
context-drop
rudyalways
No description from the publisher yet.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 5, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from rudyalways
- 0.563score
claude-router
rudyalways
Choose between the local Codex CLI and Gemini CLI from Claude Code.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
claude-gemini
rudyalways
Use the local Gemini CLI from Claude Code with the user's existing Gemini authentication or API configuration.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
image-generation
rudyalways
Generate and edit images using Gemini Flash Image, and generate videos using Veo.
SkillBFreshness: B★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get macos-use running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
macos-use skill. Agent Mart. https://agentmart.dev/skills/rudyalways-macos-use (last updated 2026-10-24)