Log inSubmit server
Droidsight logo

Droidsight

Drives an Android device over ADB with vision, input, diagnostics, app control, recording, and optional shell access.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Droidsight

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "droidsight": {
      "command": "npx",
      "args": [
        "-y",
        "@edgecasehuman/droidsight"
      ],
      "env": {
        "DROIDSIGHT_DEVICE_SERIAL": "YOUR_VALUE_HERE",
        "DROIDSIGHT_ADB_PATH": "YOUR_VALUE_HERE",
        "DROIDSIGHT_LOCAL_ROOT": "YOUR_VALUE_HERE",
        "DROIDSIGHT_DEVICE_PIN": "YOUR_VALUE_HERE",
        "DROIDSIGHT_ALLOW_SHELL": "YOUR_VALUE_HERE",
        "DROIDSIGHT_DEBUG_LOG": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @edgecasehuman/droidsight

Process exited before answering initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 8d ago.

Overview

The droidsight MCP server connects an MCP client to a real Android device through ADB and returns the resulting screen with actions. It combines screenshots, accessibility hierarchy, OCR, template matching, structured input, app management, diagnostics, file transfer, recording, and device controls. Use it for Android UI automation, testing, inspection, and controlled device operations where an agent needs visual feedback after each action. The server is a local controller rather than a sandbox, so it should only access trusted devices and clients.

Use cases

  • Automate Android interfaces with visual feedback
  • Test apps across accessibility and OCR-based workflows
  • Inspect app state, logs, notifications, and processes
  • Record gestures and replay repeatable interactions
  • Transfer files and collect device diagnostics

Key features

  • ADB-based Android device control
  • Screenshot, OCR, hierarchy, and template search
  • Structured input and gesture replay
  • App management and instrumentation
  • Device diagnostics and file operations
  • Optional unrestricted shell and macro tools

Tools31

What Droidsight lets your agent do. Expand a tool for its parameters.

Self-reported~723 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

5/5 checks healthy over the last 42d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 22h ago via OSV.dev · @edgecasehuman/droidsight (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars4Stargazers on the source repository.
npm downloads154Package downloads in the last 30 days.
Last commit14d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Tools exposed31Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Droidsight works

What droidsight MCP server does

The droidsight MCP server exposes an Android device to an MCP client through ADB. It can inspect the current screen with screenshots, OCR, accessibility data, element searches, and template matching, then perform input actions such as taps, typing, key events, swipes, smart taps, and IME operations. Vision results include coordinate metadata, while element snapshots can provide precomputed centers so an agent does not need to calculate tap coordinates.

Beyond UI interaction, the server supports application lifecycle operations, intent and URL launching, device information, clipboard access, lock and rotation control, network settings, sensor simulation, notifications, screen recording, and health checks. Diagnostic features include logcat access, event buffers, log filtering, notification inspection, activity and process details, stack traces, on-device SQLite queries, file hashing, and application-data deletion.

How it works

The process communicates through newline-delimited JSON-RPC 2.0 on standard input and output. ADB must be available through the system path, Android SDK environment settings, or an explicit executable path. When multiple authorized devices are visible, the target must be selected by serial rather than guessed.

A background H.264 stream can provide the screen produced by an action in the same tool result. Screenshots default to 720 pixels wide and may be downscaled, so returned image metadata describes the device dimensions, scale, origin, and coordinate space. OCR boxes, hierarchy bounds, template matches, and input coordinates use device coordinates. The vision tool's indexed element workflow can avoid manual conversion.

Setup and configuration

The simplest installation uses npx -y @edgecasehuman/droidsight, which downloads a platform binary and does not require build tools. The project can also be installed with Cargo or built from source; those compilation paths require NASM because the H.264 decoder has native assembly components. The resulting server can be registered as a standard stdio MCP process.

Set DROIDSIGHT_DEVICE_SERIAL when more than one authorized device is available. DROIDSIGHT_ADB_PATH selects a specific ADB executable, and DROIDSIGHT_LOCAL_ROOT restricts host paths used for APK installation and file transfers. DROIDSIGHT_DEVICE_PIN supplies a runtime PIN for automatic unlock actions and should not be stored in source or checked-in configuration.

Tools and capabilities

The droidsight MCP server publishes tools for:

  • Screen capture, streaming, hierarchy inspection, OCR, element lookup, smart waits, and text-triggered taps.
  • Direct input, bounded validated flows, gesture recording and replay, app installation and lifecycle control.
  • Device, network, sensor, accessibility, overlay-permission, notification, and companion controls.
  • Logcat, semantic events, crash information, process inspection, file transfer, SQLite queries, and hashing.
  • Screen recording for up to 180 seconds, with the resulting file retained on the device.

Shell and macro tools are hidden unless DROIDSIGHT_ALLOW_SHELL=1 is set.

Limitations and notes

The droidsight MCP server has broad authority over the selected device. System control can grant screen-reading and input-injection access across applications, notification inspection may expose unredacted message content, and shell mode permits unrestricted device shell commands. Use it only with a device and MCP client you trust.

Destructive application operations require confirm_destructive, but shell access has no command filtering. GPS mocking works only on an emulator. Session marker tools acknowledge calls without retaining server state. File operations are confined to DROIDSIGHT_LOCAL_ROOT on the host, while screen recordings remain on the Android device.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Droidsight

droidsight is an MCP server that connects an MCP client to a real Android device through ADB. Its main tools provide screen and hierarchy inspection, OCR and element search, input actions, app management, diagnostics, device controls, file transfer, recording, and optional shell access.

Install it with `npx -y @edgecasehuman/droidsight`. This downloads a prebuilt binary without requiring build tools. You can also use Cargo or build from source, but both compilation routes require NASM for the native H.264 decoder.

Set `DROIDSIGHT_DEVICE_SERIAL` to the serial shown by `adb devices` when more than one authorized device is available. The server refuses to choose between multiple authorized devices automatically.

Yes. Its vision query tool supports OCR, element search, and template matching, while the `elements` and `tap_element` actions use indexed snapshots and precomputed element centers. This avoids manual coordinate arithmetic for supported elements.

Set `DROIDSIGHT_ALLOW_SHELL=1` before starting the server. This publishes arbitrary shell and macro tools, which provide broad ADB shell authority and do not filter commands.

Related MCP servers

All in OS Automation All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewDroidsight AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/droidsight?style=directory)](https://allmcps.com/mcp/droidsight)
HTML Embed
<a href="https://allmcps.com/mcp/droidsight"><img src="https://allmcps.com/api/badge/droidsight?style=directory" alt="Droidsight on AllMCPs" /></a>