Local MCP server for AI agents: local YOLO-based UI-element detection (OmniParser-v2 icon detector) with per-element OCR, hash caching, and full keyboard / mouse / screen / clipboard control via pyautogui + mss.
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":"kira-mcp-2","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.
``` ██╗ ██╗██╗██████╗ █████╗ ██║ ██╔╝██║██╔══██╗██╔══██╗ █████╔╝ ██║██████╔╝███████║ ██╔═██╗ ██║██╔══██╗██╔══██║ ██║ ██╗██║██║ ██║██║ ██║ ╚═╝ ╚═╝╚═╝╚═╝ ╚═╝╚═╝ ╚═╝ local · MCP · computer-use ``` <p align="center"> <a href="https://pypi.org/project/kira-mcp/"><img alt="PyPI" src="https://img.shields.io/pypi/v/kira-mcp?color=3775A9&label=pypi"></a> <a href="https://www.python.org/downloads/"><img alt="Python 3.10+" src="https://img.shields.io/badge/python-3.10+-3776AB?logo=python&logoColor=white"></a> <a href="https://modelcontextprotocol.io"><img alt="MCP 1.2+" src="https://img.shields.io/badge/MCP-1.2+-7C3AED"></a> <a href="https://opensource.org/licenses/MIT"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-22C55E"></a> <img alt="Platforms" src="https://img.shields.io/badge/platforms-Linux%20%7C%20macOS%20%7C%20Windows-64748B"> </p> --- **kira-mcp** is a local [Model Context Protocol](https://modelcontextprotocol.io) server that gives any MCP-compatible agent host (Claude Desktop, Claude Code, Cursor, Cline, Continue, …) full **computer-use** capabilities on the host machine. > Built and tuned for **Windows**. macOS and Linux are best-effort — most tools work, but some UI conventions differ. - **Vision** — `perceive_screen` is the agent's one-shot "look at the screen" tool. It grabs the current display in memory, runs the local [microsoft/OmniParser-v2](https://huggingface.co/microsoft/OmniParser-v2.0) YOLO icon-detector on it, and returns an annotated image *plus* JSON with each element's `{id, bbox, cx, cy, confidence}` in absolute screen pixels — so the agent can pipe `cx, cy` straight into `mouse_click`. No API key, no network call. - **Desktop automation** — pixel-accurate mouse control, keyboard input (incl. chords and key holds), and clipboard read/write via [pyautogui](https://pyautogui.readthedocs.io/), [mss](https://github.com/BoboTiG/python-mss), and [pyperclip](https://github.com/aswe…
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.