Computer Use Linux MCP Server

@agent-sh

代码仓库

基本信息

分类

生产力

许可证

MIT

作者

agent-sh

关于 Computer Use Linux MCP Server

Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool

Computer Use Linux MCP Server 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块，请前往代码仓库查看安装说明。

代码仓库

Computer Use Linux MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Computer Use Linux?

Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool

How to use Computer Use Linux?

Follow the repository README to install the server and add its MCP configuration to your client.

Key features of Computer Use Linux

list_apps — running desktop apps visible to the AT-SPI registry
list_windows — compositor windows with title, app id, wm_class, focus state, client type (Wayland/X11), and bounds
focused_window — the window currently holding keyboard focus
click — by element index, semantic selector, or desktop coordinate pixels
drag — desktop coordinate drag (start / end)

Use cases of Computer Use Linux

Connect an MCP-compatible client to this repository's service.
Review the README-backed setup before enabling it in production.

常见问题

Where is the source code for Computer Use Linux?

The source code is linked from the repository URL on this page.

Does Computer Use Linux include a standard MCP config?

If the README contains a parseable MCP configuration block, it is shown in the Config tab.

生产力分类下的更多 MCP 服务器

Comuna

Comuna is a free-forever team workspace (Kanban, table, calendar, Gantt, chat, notes, wiki) where your AI is a real board member. Connect Claude or ChatGPT via MCP in 60 seconds: 80+ tools to work cards under its own ide

Tribeunal Decision-Making MCP

tribeunal

Human-in-the-loop decision-making by hybrid jury. Tribeunal is a decision platform where humans and AI agents open cases, weigh evidence and vote. 41 MCP tools + eight Agent Skills, incl. long-poll verdict awaiting, arbi

Genchi

Genchi Software Inc

Genchi shows engineering leaders a prediction of which projects are heading for a missed deadline and which aren't, from the people doing the work. Giving every engineer a way to be heard, this prediction comes from thei

QuillHub

Meeting transcripts for AI agents: search every call, read who said what, pull decisions and action items, get quotes from one person across meetings, follow deals and projects, and transcribe files or YouTube links. Hos

Daski

Daski is a remote MCP server available at https://daski.io.