๐ Wayland MCP Server
@someaka
About ๐ Wayland MCP Server
MCP Server for Wayland
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"wayland-screenshot": {
"command": "uvx",
"args": [
"wayland-mcp"
],
"env": {
"OPENROUTER_API_KEY": "",
"VLM_MODEL": "qwen/qwen2.5-vl-72b-instruct:free",
"XDG_RUNTIME_DIR": "/run/user/1000",
"WAYLAND_MCP_PORT": "4999",
"DISPLAY": ":0",
"WAYLAND_DISPLAY": "wayland-0",
"XDG_SESSION_TYPE": "wayland"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
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 openโsource license.
More Other MCP servers
Core Philosophy: Connect, Unify, Respond
mindsdbDelegate anything. It comes back done.
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
MCP Go ๐
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
XcodeBuildMCP
cameroncookeA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Nginx UI
0xJackyYet another WebUI for Nginx
Comments