← Browse
screen-mcp
88plug ★ 1
screen-mcp is an MCP server that enables Claude Code to control Linux/Wayland desktops by taking screenshots, clicking, typing, and reading any visible app through xdg-desktop-portal, with optional OCR and OmniParser icon grounding. It includes a drive-screen skill for the locate-ground-act-confirm loop and screen_watch (~1 fps) for agents to detect UI changes like humans do, all in pure Python without external paid services.
Install
> /plugin marketplace add 88plug/screen-mcp
> /plugin install screen-mcp
What it's made of
1 skill · 1 MCP server
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 1
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
screen-mcp- Talks to
- nothing external detected
Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (88plug).