agent-device
MCP server · callstack
- On your machine
agent-device is an MCP server published by callstack. Marketplaces we read that list it: 1 (Official MCP Registry). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 2026-10-11.
MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps
- Marketplaces
- 1
- Where it runs
- On your machine
agent-device - Largest published figure
- 4 971 Stars (GitHub) · Official MCP Registry
- First seen
- 2026-10-11
- Last change
- None recorded
- Verified mark
- Not marked
Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Official MCP Registry (Open the registry record) | Listed | 0.21.25 | Forks (GitHub): 332 Stars (GitHub): 4 971 |
Not marked | |
| Official MCP Registry (Open the registry record) | Listed | 0.16.9 | Forks (GitHub): 332 Stars (GitHub): 4 971 |
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.
What it can do
Runs on your machine: the AI tool starts this npm package locally: agent-device
None of the marketplaces we read publishes its tools or the settings it asks for.
What changed
Nothing has moved on this plugin since we started watching it.
The publisher
callstack · Repository: github.com/callstack/agent-device
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.
- Mobile Device MCPControl iOS and Android devices with multi-device and seamless Native/WebView support.
- Quash — Mobile App AutomationDrive Android & iOS mobile-app automation from your AI agent on locally connected devices.
- AppContextLive iOS Simulator and browser screenshots, logs, and a personal MCP hub for AI coding agents.
- mobai-mcp io.github.MobAI-App/mobai-mcpAI-powered mobile device automation for Android and iOS devices, emulators, and simulators
- ios-agentDrive a real iPhone or an iOS Simulator with an AI agent, through XCUIAutomation.
- RobotActions — AI-Driven Mobile + Web Test AutomationDrive real Android & iOS devices and web browsers from natural language for mobile + web QA.
- UIAutomator2 MCP ServerAndroid mobile automation with uiautomator2. AI bot for taps, swipes, apps, XPath testing, RPA.
- mobile-device-mcp io.github.saranshbamania/mobile-device-mcpAI control of Android/iOS devices. Screenshots, UI tree, AI vision, Flutter, video. 49 tools.
- MCP Appium - Mobile Development and Automation ServerMCP server for Appium mobile automation on iOS and Android devices with test creation tools.
- testingKobiton 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…
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)
- testingKobiton 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…
- android-emulator-qa-pluginClaude 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…
- agentiqaAI-powered QA testing agent for web and mobile apps. Agentiqa explores your app visually - like a real user with fresh eyes - and reports bugs with severity, confidence scores…
- n360-app-releaseComprehensive mobile app release testing protocol with 19 verification phases and priority classification (P0 release blockers through P3 nice-to-have). Covers API health, auth…
- testdinoUse TestDino inside Claude Code through the hosted remote MCP server to inspect test runs, debug failing test cases, manage manual tests, and run TestDino audits.
Has a listing on Claude Code: claude-plugins-official (5)
- playwright-mcp io.github.microsoft/playwright-mcpPlaywright Tools for MCP
- PostmanWork 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…
- Chrome DevTools MCPMCP server for Chrome DevTools
- mcp-appsSkills for creating MCP Apps with the MCP Apps SDK
- teamcity-cliAgent skill for interacting with TeamCity CI/CD using the teamcity CLI. Enables Claude to explore builds, view logs, start jobs, manage queues, agents, and more.
Has a listing on Claude: knowledge-work-plugins (5)
- growthbookA suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.
- browser-useGive 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…
- Desktop CommanderMCP server for terminal commands, file operations, and process management
- stackhawk-apiQuery the StackHawk platform API for security posture reporting, findings analysis, and app management. Guides agents through authentication, data retrieval, and result…
- servicenow-sdkCreate, edit, and deploy ServiceNow applications with the Fluent SDK effortlessly through Claude AI.
Has a listing on Codex: openai-curated (openai/plugins) (5)
- Test Android AppsTest Android apps with emulator workflows for reproduction, screenshots, UI inspection, log capture, and performance profiling.
- Build iOS AppsBuild 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.
- crowdstrike-falcon-foundryCrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
- SentryInspect recent issues and events in Sentry from Codex.
- Datadog (Preview)Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
Has a listing on Community GitHub marketplaces (5)
- qaQA-test a website or app and return a 1-5 quality score with evidence. Drives a Browser Use cloud browser and tunnels localhost automatically. Run as /qa <url-or-localhost-port>…
- Chrome DevTools MCPMCP server for Chrome DevTools
- DynatraceDynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
- HTTPHTTP/REST client with saved collections, env secrets, and SSRF-safe host allowlisting.
- Computer Use TurboLet any AI agent operate desktop apps on macOS, Windows and Linux, in the background and safely.
Has a listing on Copilot CLI: github/awesome-copilot (5)
- mobile-canvasView, 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…
- bd-skillsHelps GitHub Copilot investigate mobile app telemetry, diagnose crashes, manage [bitdrift](bitdrift.ai) workflows and dashboards, integrate the Capture SDK into iOS, Android, and…
- BLEASafe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
- Chrome DevTools MCPMCP server for Chrome DevTools
- automate-thisRecord 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…
Has a listing on Copilot CLI: github/copilot-plugins (5)
- canvas-appsBuild Power Apps Canvas Apps using the Canvas Authoring MCP server.
- microsoft-365-agents-toolkitToolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
- mcp-appsGenerate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
- model-appsBuild 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…
- mobile-appBuild and deploy Power Apps code apps for mobile using Expo (React Native), with native device functionality and Power Platform connectors
Has a listing on Cursor: cursor/plugins (5)
- playwright-mcp io.github.microsoft/playwright-mcpPlaywright Tools for MCP
- Agent CompatibilityCLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
- Cursor SDKBuild apps, scripts, and automations with the TypeScript SDK.
- Origin AppsSkills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
- Create PluginScaffold and validate new agent plugins.
Has a listing on Docker MCP Catalog (5)
- SmartBear MCPMCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
- mcp-server-browserbase io.github.browserbase/mcp-server-browserbaseMCP server for AI web browser automation using Browserbase and Stagehand
- playwright-mcp io.github.microsoft/playwright-mcpPlaywright Tools for MCP
- Postman MCP ServerGive your AI agents trusted access to the full Postman platform.
- testkube-mcp io.github.kubeshop/testkube-mcpMCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants
Has a listing on Official MCP Registry (5)
- Mobile Device MCPControl iOS and Android devices with multi-device and seamless Native/WebView support.
- Quash — Mobile App AutomationDrive Android & iOS mobile-app automation from your AI agent on locally connected devices.
- AppContextLive iOS Simulator and browser screenshots, logs, and a personal MCP hub for AI coding agents.
- mobai-mcp io.github.MobAI-App/mobai-mcpAI-powered mobile device automation for Android and iOS devices, emulators, and simulators
- ios-agentDrive a real iPhone or an iOS Simulator with an AI agent, through XCUIAutomation.
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.
Is this your plugin?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and can put its remote endpoint 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.