Kira Mcp

Name: Kira Mcp
Author: Anmol202005

@Anmol202005

About Kira Mcp

A local Model Context Protocol (MCP) server that gives any MCP-compatible host (Claude Desktop, Claude Code, Cursor, Cline, Continue) full computer-use control of the machine. One perceive_screen call screenshots the display, runs a bundled OmniParser-v2 YOLO icon-detector plus o

#computer-use #automation #vision #omniparser #pyautogui

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "kira-mcp": {
      "command": "kira-mcp"
    }
  }
}

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 Kira Mcp?

A local Model Context Protocol (MCP) server that gives any MCP-compatible host full computer-use control of the machine. It screenshots the display, runs a bundled OmniParser-v2 YOLO icon-detector with optional OCR, and returns click-ready pixel coordinates, along with mouse, keyboard, and clipboard automation via pyautogui. No API keys or network calls are required.

How to use Kira Mcp?

Install the package with pip install kira-mcp, then configure the server in any MCP-compatible host (e.g., Claude Desktop, Claude Code, Cursor, Cline, Continue). The server exposes the perceive_screen tool, which captures the screen and returns actionable coordinates for automation.

Key features of Kira Mcp

Screenshots the display and runs OmniParser-v2 YOLO icon detection.
Optional OCR for text recognition on screen.
Returns click-ready (cx, cy) pixel coordinates.
Full mouse, keyboard, and clipboard automation via pyautogui.
No API key required – fully local processing.
Model weights are shipped inside the package.

Use cases of Kira Mcp

Enabling an AI assistant to control desktop applications as a human would.
Automating repetitive GUI tasks without manual input.
Performing visual-based testing and interaction with software interfaces.
Integrating computer‑use abilities into MCP‑compatible coding or productivity tools.

FAQ from Kira Mcp

Does Kira Mcp require an API key or internet connection?

No. All processing is done locally with no network calls or API keys needed.

What MCP‑compatible hosts can use Kira Mcp?

It works with any host supporting the Model Context Protocol, including Claude Desktop, Claude Code, Cursor, Cline, and Continue.

How do I install Kira Mcp?

Install via pip: pip install kira-mcp. The OmnniParser-v2 YOLO weights are bundled inside the wheel, so no additional download is required.

What actions can Kira Mcp perform beyond clicking?

It can automate mouse movement, keyboard input, and clipboard operations using pyautogui, in addition to the screen capture and coordinate extraction.