Model Context Protocol server for Wayland desktop automation with VLM analysis, mouse/keyboard control, and action chaining
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"wayland-mcp-kurojs","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<div align="center"> <h1>Wayland MCP Server</h1> <strong>Model Context Protocol server for Wayland desktop automation</strong> <br> <a href="https://pypi.org/project/wayland-mcp-kurojs/"><img src="https://img.shields.io/pypi/v/wayland-mcp-kurojs?style=flat-square&logo=pypi&logoColor=white&color=3775A9" alt="PyPI Version"></a> <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.10%2B-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python 3.10+"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-GPL--3.0-A42E2B?style=flat-square&logo=gnu&logoColor=white" alt="License GPL-3.0"></a> <a href="https://modelcontextprotocol.io"><img src="https://img.shields.io/badge/MCP-compatible-3DDC84?style=flat-square" alt="MCP Compatible"></a> <a href="README.md"><img src="https://img.shields.io/badge/platform-Linux%20%7C%20Wayland-lightgrey?style=flat-square" alt="Platform Linux/Wayland"></a> <br> <a href="#features">Features</a> • <a href="#installation">Installation</a> • <a href="#usage">Usage</a> • <a href="#available-tools">API</a> • <a href="#security">Security</a> </div> --- ## Overview Wayland MCP Server lets AI assistants interact with a Wayland desktop through the Model Context Protocol. It captures the screen for visual analysis by a vision language model, controls the pointer and keyboard, and chains actions into multi-step workflows. It was built around two observations. Screenshot and automation tooling on Wayland is fragile: it depends on which binaries are installed, which protocol extensions the compositor advertises, and which portals are present on the session bus. And the usual remedy, giving an automation tool root or write access to `/dev/input`, is a security hole the user pays for every day. This server answers both. It probes the actual capabilities of the session and picks the best backend that can work, and its preferred path nee…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.