🚀 Wayland MCP Server

What is Wayland MCP Server?

Wayland MCP Server provides screenshot, analysis, mouse and keyboard control tools for modern Linux desktops running the Wayland display protocol. It is intended for users who need reliable screenshot and input simulation capabilities that existing solutions may not support under Wayland.

How to use Wayland MCP Server?

Install via uvx and add the provided JSON configuration to your MCP server config (e.g., .roo/mcp.json). Run ./setup.sh to configure permissions for input device control. Necessary environment variables include OPENROUTER_API_KEY, VLM_MODEL, XDG_RUNTIME_DIR, WAYLAND_MCP_PORT, DISPLAY, WAYLAND_DISPLAY, and XDG_SESSION_TYPE.

Key features of Wayland MCP Server

• Screenshot capture with custom VLM integration for image analysis
• Image comparison capabilities
• Mouse control (move, click, drag, scroll)
• Keyboard input (typing, key presses)
• Action chaining for complex input sequences

Use cases of Wayland MCP Server

• Automating desktop workflows by simulating mouse and keyboard actions
• Taking and analyzing screenshots with vision-language model integration
• Comparing images programmatically in a Wayland environment
• Providing reliable input control for AI assistants on modern Linux desktops

FAQ from Wayland MCP Server

What environment variables must be set?

OPENROUTER_API_KEY, VLM_MODEL, XDG_RUNTIME_DIR, WAYLAND_MCP_PORT, DISPLAY, WAYLAND_DISPLAY, and XDG_SESSION_TYPE must be configured in the MCP server environment.

How do I set up input control?

Run ./setup.sh to configure permissions for evemu-event to control input devices.

Is it safe to enable input control?

Enabling input control gives the MCP server full access to your mouse and keyboard. Only use with trusted MCP servers and models.

What dependencies are required?

The server runs via uvx and requires evemu-event for input simulation. It is developed on modern Linux with Wayland.

How is this server licensed?

It is licensed under the GPL3 open‑source license.