Karagöz
Device automation for Android emulators and phones, iOS simulators and iPhones. No daemon.
MCP server · by yagizdo
About
Karagöz is an MCP server published by yagizdo. Marketplaces we read that list it: 1 (Official MCP Registry). The last change we recorded was on 2026-11-06. As of our marketplace pass on 2026-11-14.
What it asks for
- Runs on your machine
None of the marketplaces we read publishes its tools or the settings it asks for.
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Package
npm karagoz-mcp (karagoz-mcp on npm)
- npm downloads/week: 470 (2026-11-10)
- npm downloads/month: 1 944 (2026-11-10)
- Latest version on npm: 0.4.0, published 2026-11-04
npm facts come from the public npm registry (registry.npmjs.org, api.npmjs.org). Each figure is the registry's own and is never added to another. A registry that publishes no figure shows none: no number is not zero.
Works with
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
A one-click link opens the client, which asks you to confirm before it adds the server.
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a local MCP server: npm package
Built from what Official MCP Registry declares.
claude mcp add --transport stdio karagoz-mcp -- npx -y karagoz-mcp mcp
[mcp_servers.karagoz-mcp]
command = "npx"
args = ["-y", "karagoz-mcp", "mcp"]
{
"mcpServers": {
"karagoz-mcp": {
"command": "npx",
"args": [
"-y",
"karagoz-mcp",
"mcp"
]
}
}
}
Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Official MCP Registry (Open the registry record) | Listed | 0.4.0 | Downloads/month (npm): 1 944 Downloads/week (npm): 470 Forks (GitHub): 0 Stars (GitHub): 4 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
How its figures have moved
- 2026-10-291
- 2026-11-022
- 2026-11-033
- 2026-11-064
- 2026-11-144
Each dot is a day we read a different number; flat stretches are days the number did not move. Figures of different marketplaces are never added up.
What changed
- Official MCP Registry: released version 0.4.0 (was 0.3.2)
- Official MCP Registry: released version 0.3.2 (was 0.3.1)
- Official MCP Registry: released version 0.3.1 (was 0.3.0)
- Official MCP Registry: released version 0.3.0 (was 0.2.0)
- Official MCP Registry: released version 0.2.0 (was 0.1.1)
- Official MCP Registry: description changed
- Became a product we track
- Official MCP Registry: released version 0.1.1 (was 0.1.0)
- Official MCP Registry: appeared
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
Fast Android emulator and iOS Simulator control for coding agents: screenshots, UI tree, taps, logs
-
Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
-
Drive Android emulators: screenshots, taps, swipes, keys, text, rotation and foldable postures.
-
mobai-mcp io.github.MobAI-App/mobai-mcp
AI-powered mobile device automation for Android and iOS devices, emulators, and simulators
-
Drives a real Android device over ADB and attaches the resulting screen to every action.
-
Mac app that lets AI agents drive iPhones, iOS simulators and Android: tap, type, install, logs.
-
MCP tools for testing mobile and TV apps on iOS simulators, Android phones, and Apple/Android TV.
-
Control real iOS & Android devices from AI agents; mirror one tap across a whole fleet.
-
android io.github.martingeidobler/android
Control Android devices and emulators via ADB — screenshots, UI automation, and logcat.
-
Drive iOS Simulators, iPhones, Android devices and macOS apps: UI snapshots, live viewer, recording.
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
Claude Android QA Plugin helps Claude Code test Android apps in an emulator. It can launch apps, inspect UI trees, derive safe tap coordinates, capture screenshots, and collect…
-
Kobiton brings agentic AI to mobile quality so engineers & testers can initiate testing directly from where code is built. With our Claude Code plugin, you can initiate Appium…
-
e2e-runner io.github.fastslack/e2e-runner
JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.
-
An agent skill for creating and running sandboxes on the Daytona platform.
-
Open-source browser agent driven via CDP — direct browser control, 79K stars, YC W25. browser-harness gives Claude Code direct, low-level control of a real Chrome browser via the…
Has a listing on Claude Code: claude-plugins-official (5)
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
Work with Postman from your agent: bootstrap a repo's Postman setup, mock an API before it's implemented, run collection and governance checks in CI, monitor a live endpoint…
-
firebase-mcp io.github.firebase/firebase-mcp
Gives AI development tools Firebase-specific capabilities and expertise.
-
MCP server for Chrome DevTools
-
MCP server for terminal commands, file operations, and process management
Has a listing on Claude: knowledge-work-plugins (5)
-
MCP server for terminal commands, file operations, and process management
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
-
Give Claude a real browser — your Chrome or a Browser Use Cloud browser. Use it whenever a task involves a website or web app: browsing, scraping and data extraction, filling…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Unity's official plugin for Claude Code, with curated skills for game development, monetization, and performance optimization.
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Test Android apps with emulator workflows for reproduction, screenshots, UI inspection, log capture, and performance profiling.
-
Build iOS apps with workflows for App Intents, SwiftUI UI work, Simulator mirroring in the Codex in-app browser, performance profiling, leak investigation, and simulator debugging.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build, run, test, debug, instrument, and implement local macOS apps using Xcode, SwiftUI, AppKit interop, unified logging, and shell-first desktop workflows.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
Has a listing on Community GitHub marketplaces (5)
-
Mobile device interaction automation via MCP
-
Control one to four local Android phones through bounded screenshots and allowlisted actions from Codex or DeepSeek Harness.
-
Let AI agents see and control Android and iOS phones over stdio.
-
AI agents see and drive the Android Emulator: screenshots, UI in dp, tap, dark mode, RTL, logcat.
-
Annotate a running iOS simulator in the browser and hand each note to your agent: sim-agentation itself, its MCP server, and skills for working through annotations and adding the…
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
View, create, boot, and interact with local iOS simulators and Android emulators from a GitHub Copilot canvas. The plugin also exposes the same device controls to agents through…
-
Observe and interact with explicitly selected real Android devices over authorized USB or paired wireless ADB.
-
Record your screen doing a manual process, drop the video on your Desktop, and let Copilot CLI analyze it frame-by-frame to build working automation scripts. Supports narrated…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Helps GitHub Copilot investigate mobile app telemetry, diagnose crashes, manage [bitdrift](bitdrift.ai) workflows and dashboards, integrate the Capture SDK into iOS, Android, and…
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
mobile-app
Build and deploy Power Apps code apps for mobile using Expo (React Native), with native device functionality and Power Platform connectors
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Has a listing on Cursor: cursor/plugins (5)
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Let Grok Bot reach MCP servers on your private Tailscale network: connect your own tailnet, or your team's company tailnets turned on by a team admin, with each member using their…
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Create and run persistent agent runtimes, publish ports, and manage egress, checkpoints, and images in Runta.
Has a listing on Docker MCP Catalog (5)
-
mcp-server-browserbase io.github.browserbase/mcp-server-browserbase
MCP server for AI web browser automation using Browserbase and Stagehand
-
A Model Context Protocol (MCP) server that exposes Hoverfly as a programmable tool for AI assistants like Cursor, Claude, GitHub Copilot, and others supporting MCP. It enables…
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
-
Give your AI agents trusted access to the full Postman platform.
Has a listing on Official MCP Registry (5)
-
Fast Android emulator and iOS Simulator control for coding agents: screenshots, UI tree, taps, logs
-
Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
-
Drive Android emulators: screenshots, taps, swipes, keys, text, rotation and foldable postures.
-
mobai-mcp io.github.MobAI-App/mobai-mcp
AI-powered mobile device automation for Android and iOS devices, emulators, and simulators
-
Drives a real Android device over ADB and attaches the resulting screen to every action.
Has a listing on PyPI (MCP servers) (5)
-
Drive a real iPhone or an iOS Simulator with an AI agent, through XCUIAutomation.
-
Android mobile automation with uiautomator2. AI bot for taps, swipes, apps, XPath testing, RPA.
-
MCP server for macOS desktop automation via the Accessibility API.
-
Undetectable browser automation for AI agents via the Model Context Protocol — one shared backend built for 50+ concurrent Claude Code sessions.
-
Bundles the kwin-mcp MCP server (uvx kwin-mcp) plus the kwin-desktop-automation skill that teaches session-mode selection, the observe-act-verify loop, element refs, US-QWERTY vs…
Has a listing on npm registry (MCP servers) (5)
-
mobai-mcp io.github.MobAI-App/mobai-mcp
AI-powered mobile device automation for Android and iOS devices, emulators, and simulators
-
Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
-
Model Context Protocol server for driving iOS Simulators: screenshots, UI tree, taps, app lifecycle and device staging
-
MCP server for mobile, desktop and browser automation — Android, iOS, HarmonyOS Next, Aurora OS, Desktop, and Browser
-
scrcpy-mcp io.github.JuanCF/scrcpy-mcp
MCP server for Android device control via ADB and scrcpy
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Want this mark on your plugin in our catalog?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record, and you can show this mark on the card, with live banners for your site and README. How verification works
You also get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.