Open Computer Use
Open-source Computer Use MCP for AI agents
91 followers
Open-source Computer Use MCP for AI agents
91 followers
Open Computer Use turns local desktop automation into a standard MCP service. It lets Codex, Claude Code, Gemini CLI, opencode, and custom MCP clients inspect apps, click, type, scroll, drag, and take screenshots across macOS, Linux, and Windows. It is open source, npm-installable, and designed to bring the non-intrusive Codex Computer Use experience to any agent stack.
Standardizing OS-level interactions like clicking, dragging, and typing through the Model Context Protocol is a massive step for agent interoperability. Rather than every team building custom accessibility wrappers, this allows developers to plug right into native OS controls. How does the system handle coordinate mapping if a user suddenly shifts screen resolutions or moves an app across a multi-monitor setup?
I used it and its great. Do you have per app permission feature planned in the near future?