AI Can Do Anything
The article discusses various tools and actions available for interacting with computer interfaces. It highlights the compact and granular forms of commands that can be used for tasks such as taking screenshots, managing windows, and accessing system features. The information is aimed at developers looking to enhance user experience through automation and accessibility.
- ▪The article outlines six compact tools and 97 granular tools for user interaction.
- ▪It emphasizes the importance of accessibility in driving user interfaces by element name rather than pixel-based methods.
- ▪The tools include functionalities for managing applications, clipboard operations, and browser interactions.
Opening excerpt (first ~120 words) tap to expand
Tools 6 compact tools + 97 granular › The 6 compact compounds are the recommended public surface. Each row lists the actions you pass via { "action": "…" }. The 97 granular tools (one schema per verb) are listed below for compatibility and debugging — use them when your runtime requires every primitive as a top-level MCP tool. Compound Purpose Actions computer Mouse, keyboard, screenshots. The raw I/O surface. screenshot · click · double_click · right_click · triple_click · hover · scroll · scroll_horizontal · drag · drag_path · type · key · wait accessibility Drive UI by element name, not by pixel. Survives DPI, resize, layout shifts.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Clawdcursor.