AgentSidekick

Mobile Device Testing

Testing apps on simulators, emulators and real devices. As of 2026-11-21, 67 indexed products offer it (22 with full profiles), in 1 form: 67 MCP servers. 44 were published in the last 90 days, against 9 in the 90 days before. docker-android has the most GitHub stars, 30% of the total across 59 products with their own repository.

CapabilitySegment label: Outpacing the catalogue DER

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 67 indexed · 22 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Mobile Device Testing: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1docker-androidAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agentbudtmo16k2d ago
2mobile-mcpMCP server for iOS and Android Mobile Development, Automation and Testingmobile-next11k3d ago
3lamdaAndroid Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one-click MITM, built-in Frida, proxy/VPN/frp/P2P networking, MCP/Agent, 160+ APIs, designed for multi-device clusters and engineered deployments.firerpa8.8k6d ago
4agent-deviceOpen source device layer for AI agents: control mobile, web, TV, and desktop apps over MCPcallstack5.5ktoday
5agent-deviceLet AI agents inspect, control, and debug real iOS, Android, desktop, and TV appscallstackincubator5.5ktoday
6ArgentDrive iOS, Android, HarmonyOS, TV, Mac and Electron/web apps from your coding agentsoftware-mansion3.2ktoday
7simutilUtilities for Android emulators, iOS simulators and real devices: launch, stream, control, record and automate them from a desktop app, TUI and CLIdungngminh1.2k3d ago
8DroidlineLet an AI agent see and use a real Android phone over Wi-Fi, without ADB or root.KnifeLemon55818d ago
9iPhone UseDrive a real iPhone from a Mac: read the screen as text, tap, type, scroll, replay saved flows.leeguooooo512today
10mirroir-mcpDrive a stock iPhone via iPhone Mirroring: no Developer Mode, Xcode or WDA. LLM-free skill replay.jfarcand3951d ago

All 22 profiled MCP servers with this capability

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Cursor1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
Android3856.7%
Xcode / iOS1826.9%
Figma11.5%
Playwright11.5%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
mobile testing9
appium15
ios simulator21
android emulator18
mobile app testing0
device farm1
xcuitest3
maestro mobile0

Segment statistics

Whole catalogue (67 indexed products). Calculated 2026-11-21.

67DERIndexed products22 with full profiles
44DERLaunched, last 90 days9 in the 90 days before
67DERMomentum vs catalogue50 = same pace as the catalogue
30%DERLargest project's share of starsAcross 59 products with their own repository
0.185DERConcentration (HHI)About 5 equal-sized projects’ worth; moderately concentrated
3SRCMedian starsPer product with its own repository
78%DEROpen sourceMarked open source; unknown counts as not

Outpacing the catalogue. Mid-sized among capabilities, with launches growing faster than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.185 means stars are spread as if across about 5 equally popular projects — moderately concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .