MCP servers and skills: search, filter by where they run, and compare.
MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland — 29 tools for virtual and live sessions
PythonMIT★ 71No key
Headless MCP server that gives AI agents an isolated, sandboxed X11 GUI to launch and drive Linux desktop apps
SkillApache-2.0★ 1Few starsNo key
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
SkillApache-2.0★ 39kNo key
Agent skill for Claude Code, Codex and Cursor: repeatable screenshots of GUI desktop apps on an isolated Xvfb display, driven via python-Xlib (XTEST) and annotated with ImageMagick
SkillMIT★ 6No key
MCP server giving an AI agent grounded control of a real computer: GUI (OS accessibility), browser (CDP) and system, behind a policy kernel.
SkillApache-2.0★ 3Few starsNo key
Typed decision advice for application and browser action selection from supplied text evidence. Operator-reviewed; no native actuation.
SkillMIT★ 3Few starsNo key
Windows desktop automation via W3C WebDriver protocol — like ChromeDriver, but for Windows apps
SkillMIT★ 18No key
MCP server for Windows desktop automation. Incremental perception instead of a screenshot per step: measured 16.9x fewer tokens per action than the alternatives, with the benchmarks to check it.
PythonMIT★ 4Few starsNo key
Separate Linux desktops for AI agents: headless Wayland sessions an agent drives over MCP or CLI, with screenshots, accessibility, human takeover and persistent logins, while you keep using your own s
PythonMIT★ 3Few starsNo key
Headless Excel formula engine (129+ functions), Native MCP Server (xlsx-mcp), SIMD SSE2 math engine, and Office Ribbon desktop spreadsheet app
PythonMIT★ 2Few starsNo key
A lightweight local server for the XPathy Chrome Extension — enabling conversion, validation, and evaluation of XPathy snippets into real XPath expressions. The server parses user-written XPathy synta
SkillMIT★ 1Few starsNo key
Obsidian-headless and multiple other tools combined together to create a multi functional Obsidian App for Home Assistant
SkillBSD-3-Clause★ 2Few starsNo key
Control web pages using natural language commands through a lightweight, TypeScript-based GUI agent integrated into your webpage.
SkillMIT★ 1Few starsNo key
A professional web interface for converting files (PDF, Word, Excel, Images, Audio, HTML) to Markdown using Microsoft's MarkItDown.
SkillMIT★ 2Few starsNo key
An autonomous AI pipeline that bypasses bot-protections to scrape academic job boards, using a scheduled LLM agent to evaluate PhD opportunities against your CV.
SkillMITFew starsNo key
Agentic Slicer: give AI agents and apps the official Snapmaker Orca engine. Headless 3MF to G-code, project editing and shared REST/MCP.
PythonAGPL-3.0★ 1Few starsNo key
Parallel, focus-safe browser and native macOS automation for Claude Code
SkillMITFew starsNo key
Open-source Windows RPA and MCP server for AI agents — UIA desktop automation, browser DOM automation, ERP workflows, and fast element-level execution beyond screenshot-by-screenshot Computer Use.
PythonMIT★ 1Few starsNo key
MCP server for native Qt application automation. Inject into any running QWidget or QML app, snapshot the UI tree, find elements by text/type/property, click, type and read state from Claude, Cursor o
MCPLink only★ 6
Who stands behind it
